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. 2769
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs containing the word "turn"

    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
    373
    +0.12
    0.5%
    195
    +0.12
    0.5%
    45
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.12
    0.05
    195
    +0.12
    0.04
    184
    +0.10
    0.04
    Negative Logits
    è¦ļéĨĴ
    -0.85
    ropolitan
    -0.65
    capacity
    -0.63
    lain
    -0.63
    mma
    -0.62
    ording
    -0.62
    foundation
    -0.61
    eper
    -0.59
    accompan
    -0.58
    riad
    -0.58
    POSITIVE LOGITS
    Ī
    0.78
    buck
    0.77
    coat
    0.77
     into
    0.74
     awa
    0.71
    ¸
    0.70
     sour
    0.70
     traitor
    0.70
    ĸ
    0.70
     tides
    0.70
    Activations Density 0.665%

    No Known Activations