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 49152
    5. 8-RES_FS49152-JB
    6. 37079
    Prev
    Next
    INDEX
    Explanations

    references to the name "Issa" or similar variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    13
    +0.12
    0.5%
    463
    +0.12
    0.5%
    649
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    688
    +0.12
    0.01
    13
    +0.12
    0.01
    232
    +0.11
    0.01
    Negative Logits
     Gibbs
    -0.64
     Beir
    -0.64
    ©¶æ
    -0.64
    oad
    -0.63
    ctors
    -0.63
     Worker
    -0.62
    hedon
    -0.62
     Whole
    -0.60
     underest
    -0.59
     Shell
    -0.59
    POSITIVE LOGITS
    ificant
    1.11
    insula
    1.07
    ues
    1.07
    uing
    1.01
    uably
    1.00
    ific
    0.93
    ificantly
    0.91
    acle
    0.90
    ued
    0.88
    uers
    0.86
    Activations Density 0.010%

    No Known Activations