© 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 49152
    9. 8-RES_FS49152-JB
    11. 41589
    Prev
    Next
    INDEX
    Explanations

    references to individuals with the name "Low"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    99
    +0.12
    0.6%
    699
    +0.10
    0.5%
    640
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.12
    0.01
    494
    +0.10
    0.01
    699
    +0.10
    0.01
    Negative Logits
    natureconservancy
    -0.80
    andise
    -0.78
    UAL
    -0.77
    ä½ľ
    -0.76
    IBLE
    -0.72
    soType
    -0.71
    tnc
    -0.70
    clave
    -0.67
    arium
    -0.67
    ilage
    -0.67
    POSITIVE LOGITS
    ered
    1.13
    enthal
    1.12
    est
    0.99
    down
    0.97
    rey
    0.88
    enstein
    0.87
    ering
    0.84
    reys
    0.80
    erer
    0.77
    ell
    0.77
    Activations Density 0.014%

    No Known Activations