© 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 24576
    9. 8-RES_FS24576-JB
    11. 9532
    Prev
    Next
    INDEX
    Explanations

    references to political discussions and negotiations, particularly involving Syria, the United Nations, and opposition perspectives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    175
    +0.10
    0.5%
    456
    +0.09
    0.4%
    385
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    632
    +0.10
    0.05
    175
    +0.09
    0.04
    456
    +0.09
    0.04
    Negative Logits
     Attribution
    -0.66
     HF
    -0.61
    utterstock
    -0.60
     browsing
    -0.60
     disse
    -0.60
     trim
    -0.59
    illac
    -0.59
    ãĤ©
    -0.59
     folders
    -0.59
    ãĥ¼ãĥĨãĤ£
    -0.59
    POSITIVE LOGITS
    S
    1.04
    $.
    0.89
     Nations
    0.87
    Va
    0.84
     Soccer
    0.78
    N
    0.78
    CLASSIFIED
    0.75
    NAT
    0.75
     Geological
    0.72
     States
    0.70
    Activations Density 0.040%

    No Known Activations