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. 12209
    Prev
    Next
    INDEX
    Explanations

    legal documents and official records related to criminal cases

    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
    224
    +0.13
    0.6%
    373
    +0.13
    0.6%
    730
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.13
    0.03
    234
    +0.13
    0.03
    230
    +0.12
    0.03
    Negative Logits
    atorial
    -0.78
    culosis
    -0.74
    Travel
    -0.73
    ãĥĥãĤ¯
    -0.71
    otin
    -0.70
    acea
    -0.68
    atism
    -0.68
    ogenic
    -0.68
    obyl
    -0.66
    ãĥĺ
    -0.65
    POSITIVE LOGITS
     affidavit
    0.98
     obtained
    0.96
     sergeant
    0.89
     cited
    0.84
     Sgt
    0.82
     detailing
    0.80
     affidav
    0.80
     filed
    0.79
     redacted
    0.77
     records
    0.77
    Activations Density 0.068%

    No Known Activations