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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 888
    Prev
    Next
    INDEX
    Explanations

    locations or events related to cities and conferences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    668
    +0.12
    0.6%
    7
    +0.11
    0.5%
    55
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.12
    0.09
    224
    +0.11
    0.11
    329
    +0.10
    0.08
    Negative Logits
    20439
    -0.73
     Crimean
    -0.66
    ãĤ§
    -0.63
    peat
    -0.61
    Lear
    -0.61
    hra
    -0.60
    isation
    -0.60
    bread
    -0.59
    lihood
    -0.59
    onomy
    -0.58
    POSITIVE LOGITS
    ;;;;;;;;;;;;
    0.88
    atche
    0.81
    quartered
    0.77
     Junction
    0.71
    ometown
    0.70
    .,
    0.70
    .;
    0.68
    soDeliveryDate
    0.67
    essee
    0.67
     specializing
    0.66
    Activations Density 1.996%

    No Known Activations