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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1728
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Now that."

    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
    157
    +0.11
    0.5%
    393
    +0.10
    0.5%
    476
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    582
    +0.11
    0.02
    172
    +0.10
    0.02
    397
    +0.10
    0.02
    Negative Logits
    aro
    -0.71
    ocaust
    -0.68
    uty
    -0.68
    ubs
    -0.68
    æ©
    -0.66
    WAYS
    -0.65
    assadors
    -0.65
    oeuv
    -0.65
    ãĥĺ
    -0.62
    ands
    -0.62
    POSITIVE LOGITS
     we
    0.77
    rely
    0.73
     pesky
    0.71
     wraps
    0.64
     they
    0.63
     sounds
    0.61
     settles
    0.60
     he
    0.60
    ched
    0.60
    adays
    0.59
    Activations Density 0.068%

    No Known Activations