© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 414
    Prev
    Next
    INDEX
    Explanations

    terms related to business partnerships or collaborations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    145
    +0.10
    0.5%
    247
    +0.10
    0.5%
    656
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.10
    0.02
    575
    +0.10
    0.03
    537
    +0.10
    0.03
    Negative Logits
    aston
    -0.84
    ãĥ©ãĥ³
    -0.72
    ihil
    -0.70
    ibrary
    -0.69
    SpaceEngineers
    -0.69
    ux
    -0.68
    kefeller
    -0.67
     Reincarn
    -0.67
    anwhile
    -0.67
    ourning
    -0.67
    POSITIVE LOGITS
     partner
    1.04
    hips
    1.02
     partners
    0.99
     Partner
    0.77
    heses
    0.75
    ially
    0.67
    loo
    0.66
    hood
    0.64
    cially
    0.63
    DN
    0.63
    Activations Density 0.068%

    No Known Activations