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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 26352
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to outlining or summarizing information

    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
    195
    +0.12
    0.5%
    679
    +0.11
    0.5%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.12
    0.01
    679
    +0.11
    0.01
    672
    +0.11
    0.01
    Negative Logits
    inos
    -0.71
     [+
    -0.68
    eno
    -0.68
    enos
    -0.67
    taboola
    -0.65
    die
    -0.63
    avery
    -0.63
    ni
    -0.62
    Pear
    -0.61
    ão
    -0.61
    POSITIVE LOGITS
     outlines
    1.21
     outline
    1.09
     plans
    0.96
     outlining
    0.85
     guidelines
    0.82
     strategies
    0.81
     principles
    0.81
     goals
    0.79
     specifics
    0.78
     how
    0.77
    Activations Density 0.019%

    No Known Activations