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. 12198
    Prev
    Next
    INDEX
    Explanations

    references to autonomous vehicles (AVs) and their associated values or metrics

    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
    343
    +0.12
    0.6%
    632
    +0.11
    0.5%
    538
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.12
    0.01
    632
    +0.11
    0.01
    538
    +0.11
    0.01
    Negative Logits
    coat
    -0.79
    tons
    -0.77
    mens
    -0.71
     Gallup
    -0.71
    cloth
    -0.70
    court
    -0.66
     Coke
    -0.65
    meat
    -0.64
    beer
    -0.63
    ters
    -0.63
    POSITIVE LOGITS
    ISION
    1.05
    iew
    1.01
    ISE
    0.97
    irtual
    0.97
    oice
    0.96
    EMENT
    0.96
    IC
    0.94
    ILLE
    0.93
    ENG
    0.92
    ILA
    0.88
    Activations Density 0.003%

    No Known Activations