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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 488
    Prev
    Next
    INDEX
    Explanations

    phrases related to following or copying someone's lead or actions

    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
    679
    +0.15
    0.7%
    290
    +0.12
    0.6%
    665
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.15
    0.07
    418
    +0.12
    0.06
    290
    +0.10
    0.04
    Negative Logits
    cer
    -0.71
    voy
    -0.65
    bodied
    -0.65
    atonin
    -0.64
    hya
    -0.64
    pmwiki
    -0.63
    inese
    -0.63
    ldom
    -0.63
    flo
    -0.63
    vere
    -0.63
    POSITIVE LOGITS
     suit
    1.01
     closely
    0.92
     footsteps
    0.79
    İĭ
    0.73
    pend
    0.71
    ansen
    0.69
    suit
    0.68
     instructions
    0.68
    edient
    0.68
     Suit
    0.65
    Activations Density 1.498%

    No Known Activations