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 3072
    5. 8-RES_FS3072-JB
    6. 369
    Prev
    Next
    INDEX
    Explanations

    phrases related to political leadership and unity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    87
    +0.34
    1.9%
    64
    +0.09
    0.5%
    620
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.34
    -0.10
    575
    +0.09
    0.19
    409
    +0.07
    0.09
    Negative Logits
    udos
    -0.48
    earchers
    -0.47
    idav
    -0.46
     Variant
    -0.45
    urai
    -0.45
    bnb
    -0.44
     spokesman
    -0.43
     à¨
    -0.43
    aez
    -0.43
    ische
    -0.43
    POSITIVE LOGITS
    $.
    0.64
    %.
    0.64
    }.
    0.58
    '.
    0.56
    )).
    0.55
    .�
    0.53
    ]).
    0.53
    ]."
    0.51
    .''.
    0.51
    ".
    0.51
    Activations Density 8.823%

    No Known Activations