© 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. 18460
    Prev
    Next
    INDEX
    Explanations

    mentions of colleges or universities

    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
    575
    +0.12
    0.5%
    11
    +0.12
    0.5%
    99
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.12
    0.03
    302
    +0.12
    0.02
    99
    +0.10
    0.02
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.71
     eggs
    -0.62
    NVIDIA
    -0.62
     bre
    -0.62
     latent
    -0.58
     BLM
    -0.58
    chenko
    -0.57
    Lex
    -0.57
     headlights
    -0.55
    DEN
    -0.55
    POSITIVE LOGITS
    Hum
    0.83
    arton
    0.80
    erton
    0.80
    ritch
    0.79
    essor
    0.77
    intendent
    0.77
    Grade
    0.77
     Dublin
    0.76
    house
    0.76
    hurst
    0.76
    Activations Density 0.015%

    No Known Activations