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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23664
    Prev
    Next
    INDEX
    Explanations

    questions and explanations regarding processes and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    •How
    manner2

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    195
    +0.11
    0.5%
    236
    +0.10
    0.5%
    263
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.11
    0.06
    60
    +0.10
    0.04
    483
    +0.10
    0.04
    Negative Logits
    oubted
    -0.69
    topic
    -0.67
    ãģĮ
    -0.60
    ãģ¨
    -0.60
    odder
    -0.59
    izu
    -0.59
     territory
    -0.58
    peak
    -0.57
    ãĥĩãĤ£
    -0.57
    oubt
    -0.57
    POSITIVE LOGITS
    soever
    0.96
    beit
    0.82
    ls
    0.78
    lers
    0.73
    ling
    0.71
     much
    0.69
    rencies
    0.68
    ells
    0.67
    lings
    0.67
     they
    0.67
    Activations Density 0.076%

    No Known Activations