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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7318
    Prev
    Next
    INDEX
    Explanations

    websites and links in text

    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
    640
    +0.13
    0.6%
    284
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.13
    0.04
    515
    +0.11
    0.03
    409
    +0.10
    0.03
    Negative Logits
     grounding
    -0.78
     scaling
    -0.74
     snipers
    -0.71
     accent
    -0.71
     recess
    -0.70
     contraction
    -0.69
     aging
    -0.69
     leaving
    -0.69
     marked
    -0.68
     sway
    -0.68
    POSITIVE LOGITS
    org
    1.54
    com
    1.53
    blogspot
    1.45
    wordpress
    1.43
    tumblr
    1.36
    net
    1.34
    info
    1.30
    github
    1.29
    biz
    1.29
    edu
    1.28
    Activations Density 0.036%

    No Known Activations