Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 1357
    Prev
    Next
    INDEX
    Explanations

    passages related to game controls and player feedback

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    76
    +0.10
    0.4%
    103
    +0.10
    0.4%
    208
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.10
    0.08
    724
    +0.10
    0.09
    8
    +0.08
    0.07
    Negative Logits
    yet
    -0.77
    externalActionCode
    -0.71
    ENGTH
    -0.69
     Integrity
    -0.68
     Regulation
    -0.66
    utenberg
    -0.65
     Melt
    -0.64
    afia
    -0.64
    vich
    -0.64
     Dianne
    -0.63
    POSITIVE LOGITS
    entimes
    1.56
     overlooked
    1.10
    times
    1.04
     referred
    1.04
     mistaken
    1.00
     times
    0.95
    pmwiki
    0.93
     resorted
    0.92
     errone
    0.90
     accompanied
    0.89
    Activations Density 1.780%

    No Known Activations