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 24576
    5. 8-RES_FS24576-JB
    6. 23342
    Prev
    Next
    INDEX
    Explanations

    references to different environments or settings

    oai_token-act-pair · gpt-4o-miniTriggered 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
    460
    +0.13
    0.6%
    288
    +0.10
    0.4%
    132
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.08
    575
    +0.10
    0.07
    460
    +0.09
    0.06
    Negative Logits
    apego
    -0.75
    ophy
    -0.65
    utenberg
    -0.61
    Grand
    -0.58
    ammers
    -0.57
    rehensive
    -0.56
     Responsibility
    -0.55
    missing
    -0.55
    erity
    -0.55
    ãĥ¤
    -0.54
    POSITIVE LOGITS
     surrounded
    0.96
     manner
    0.82
     presided
    0.80
     flanked
    0.78
     overseen
    0.78
     limbo
    0.77
     guise
    0.76
     guiActiveUnfocused
    0.73
     somewhere
    0.72
     overlooking
    0.72
    Activations Density 0.395%

    No Known Activations