© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 9564
    Prev
    Next
    INDEX
    Explanations

    information related to military and political situations, as well as societal issues such as food insecurity, veterans' challenges, lead-free products, drug policies, and healthcare

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    185
    +0.09
    0.4%
    196
    +0.09
    0.4%
    576
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.09
    0.07
    576
    +0.09
    0.04
    724
    +0.09
    0.08
    Negative Logits
     sche
    -0.76
    ãĤ¤ãĥĪ
    -0.69
    kered
    -0.69
     propri
    -0.68
     tink
    -0.68
    kat
    -0.68
    ocular
    -0.67
    Appearance
    -0.67
    tone
    -0.67
     directional
    -0.66
    POSITIVE LOGITS
    population
    1.16
     estimated
    1.14
     median
    1.08
     annually
    1.07
     annual
    1.05
     worldwide
    1.03
    Ranked
    1.03
     population
    1.03
     average
    1.02
    Population
    1.01
    Activations Density 1.631%

    No Known Activations