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 6144
    5. 8-RES_FS6144-JB
    6. 4470
    Prev
    Next
    INDEX
    Explanations

    Roman numerals and special characters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    420
    +0.16
    0.7%
    541
    +0.11
    0.5%
    659
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.16
    0.05
    326
    +0.11
    0.04
    420
    +0.10
    0.03
    Negative Logits
    oulos
    -0.89
    ional
    -0.88
    iary
    -0.86
    izoph
    -0.85
    iated
    -0.83
    icals
    -0.83
    ivia
    -0.82
    ities
    -0.82
    iaries
    -0.82
    alos
    -0.79
    POSITIVE LOGITS
    llo
    1.35
    lla
    1.25
    cki
    1.13
    utenant
    1.04
    hl
    0.93
    getic
    0.91
    ces
    0.87
    lli
    0.87
    ll
    0.85
    ux
    0.84
    Activations Density 0.351%

    No Known Activations