© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 8015
    Prev
    Next
    INDEX
    Explanations

    locations or places, specifically city names

    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
    76
    +0.10
    0.5%
    86
    +0.10
    0.5%
    167
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    76
    +0.10
    0.03
    574
    +0.10
    0.02
    86
    +0.10
    0.02
    Negative Logits
    etsk
    -0.98
    iotic
    -0.95
    itude
    -0.86
    pmwiki
    -0.83
    iosis
    -0.83
    uous
    -0.83
    orescence
    -0.83
    ibly
    -0.81
    terday
    -0.80
    peria
    -0.78
    POSITIVE LOGITS
     Council
    1.15
    wide
    1.08
    scape
    1.03
     Hall
    0.99
    hall
    0.97
     Halls
    0.96
    Lab
    0.90
     council
    0.85
     Islanders
    0.85
     Coun
    0.84
    Activations Density 0.033%

    No Known Activations