© 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 24576
    5. 8-RES_FS24576-JB
    6. 6930
    Prev
    Next
    INDEX
    Explanations

    information related to sports statistics and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    116
    +0.12
    0.6%
    42
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    116
    +0.12
    0.04
    366
    +0.11
    0.03
    460
    +0.10
    0.03
    Negative Logits
    IRC
    -0.67
     Patreon
    -0.61
     Relationship
    -0.60
     Constant
    -0.59
     RELEASE
    -0.57
     Sac
    -0.57
     Crisis
    -0.55
     conventions
    -0.55
    ãĤ¹ãĥĪ
    -0.54
    Rules
    -0.54
    POSITIVE LOGITS
     overall
    0.97
     among
    0.89
     nationally
    0.87
     percentile
    0.86
     tier
    0.86
     amongst
    0.85
    ranked
    0.83
     ranked
    0.82
    Tier
    0.82
    retty
    0.82
    Activations Density 0.069%

    No Known Activations