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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 40088
    Prev
    Next
    INDEX
    Explanations

    words related to cancellation and discontinuation

    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
    114
    +0.12
    0.5%
    710
    +0.12
    0.5%
    250
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.12
    0.01
    118
    +0.12
    0.01
    98
    +0.09
    0.01
    Negative Logits
    ovych
    -0.66
     JUSTICE
    -0.63
     ItemLevel
    -0.61
    JV
    -0.61
     Garrison
    -0.61
     recoil
    -0.61
     Tuc
    -0.61
     Refuge
    -0.60
    uyomi
    -0.59
     Princ
    -0.59
    POSITIVE LOGITS
    oning
    1.03
    ctions
    0.92
    ading
    0.92
    onement
    0.90
    cend
    0.85
    rency
    0.83
    ll
    0.82
    oling
    0.82
    asion
    0.81
    zens
    0.80
    Activations Density 0.007%

    No Known Activations