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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 8340
    Prev
    Next
    INDEX
    Explanations

    information related to technical specifications, regulations, and details

    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
    314
    +0.13
    0.6%
    610
    +0.10
    0.5%
    640
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    610
    +0.13
    0.03
    560
    +0.10
    0.02
    314
    +0.09
    0.01
    Negative Logits
    edIn
    -0.60
     Qiao
    -0.57
     overc
    -0.56
     chant
    -0.56
     suppressed
    -0.56
     Rohingya
    -0.55
     searched
    -0.55
     Sig
    -0.54
     cheated
    -0.54
     inspected
    -0.54
    POSITIVE LOGITS
    equ
    0.95
    pair
    0.92
    distance
    0.90
    surface
    0.90
    toe
    0.88
    cent
    0.87
    center
    0.87
    browser
    0.86
    asses
    0.86
    aft
    0.85
    Activations Density 0.032%

    No Known Activations