© 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. 37575
    Prev
    Next
    INDEX
    Explanations

    references to specific locations in San Francisco

    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
    330
    +0.11
    0.5%
    323
    +0.10
    0.4%
    578
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.11
    0.01
    323
    +0.10
    0.01
    219
    +0.10
    0.01
    Negative Logits
    lain
    -0.89
    stall
    -0.81
    abase
    -0.80
    taker
    -0.74
    pins
    -0.74
    eering
    -0.73
    gie
    -0.69
    pin
    -0.68
    eer
    -0.65
    staking
    -0.64
    POSITIVE LOGITS
    PD
    1.10
    WA
    1.03
    ML
    0.94
    DP
    0.94
    RA
    0.93
    SF
    0.91
    DT
    0.90
    RI
    0.90
    DC
    0.90
    DF
    0.89
    Activations Density 0.004%

    No Known Activations