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. 43394
    Prev
    Next
    INDEX
    Explanations

    the name "Ren" and variations of it

    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
    223
    +0.11
    0.5%
    195
    +0.10
    0.4%
    439
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.11
    0.01
    112
    +0.10
    0.01
    232
    +0.10
    0.01
    Negative Logits
     NETWORK
    -0.68
    Ö¼
    -0.66
    stakes
    -0.65
    OOL
    -0.63
    milo
    -0.62
    =-=-
    -0.62
     POLIT
    -0.62
     Speedway
    -0.62
     briefs
    -0.61
    ĨĴ
    -0.60
    POSITIVE LOGITS
    unciation
    1.18
    owned
    1.09
    unci
    1.08
    issance
    1.06
    ovation
    1.06
    ouncing
    1.00
    ault
    1.00
    aming
    0.94
    umbered
    0.89
    emy
    0.89
    Activations Density 0.003%

    No Known Activations