© 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. 19414
    Prev
    Next
    INDEX
    Explanations

    weather-related terms and locations

    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
    6
    +0.13
    0.6%
    640
    +0.12
    0.5%
    470
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.13
    0.10
    640
    +0.12
    0.06
    679
    +0.09
    0.06
    Negative Logits
     synthes
    -0.92
     quir
    -0.81
     hybrids
    -0.79
    undai
    -0.74
    ocamp
    -0.72
     aggreg
    -0.71
     lunar
    -0.70
     immersion
    -0.70
     glim
    -0.69
     distilled
    -0.69
    POSITIVE LOGITS
     pic
    1.43
    ðŁĺ
    1.28
     :(
    1.15
    sic
    1.11
     https
    1.10
    https
    1.10
     Shame
    1.09
     ðŁĺ
    1.09
     :)
    1.08
    ðŁ
    1.07
    Activations Density 0.328%

    No Known Activations