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 3072
    5. 8-RES_FS3072-JB
    6. 1491
    Prev
    Next
    INDEX
    Explanations

    advice or instructions related to success and decision-making

    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
    314
    +0.15
    0.7%
    651
    +0.11
    0.5%
    140
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.15
    0.10
    314
    +0.11
    -0.00
    140
    +0.09
    0.09
    Negative Logits
     constitu
    -0.67
     destro
    -0.63
     withd
    -0.61
     davidjl
    -0.60
    ĺħ
    -0.59
     exha
    -0.58
     Bastard
    -0.58
    aples
    -0.57
    EStreamFrame
    -0.55
    IZE
    -0.55
    POSITIVE LOGITS
    ings
    1.69
    able
    1.66
    ables
    1.63
    away
    1.48
    ability
    1.42
    aways
    1.41
    ers
    1.31
    outs
    1.30
    downs
    1.28
    ments
    1.23
    Activations Density 1.988%

    No Known Activations