© 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 49152
    5. 8-RES_FS49152-JB
    6. 25742
    Prev
    Next
    INDEX
    Explanations

    references to blood and injuries

    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
    581
    +0.12
    0.6%
    408
    +0.12
    0.5%
    467
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    557
    +0.12
    0.03
    362
    +0.12
    0.03
    637
    +0.11
    0.02
    Negative Logits
    YN
    -0.89
    OPA
    -0.87
     sidx
    -0.84
    OUP
    -0.84
    IRC
    -0.83
    ãĤ´ãĥ³
    -0.81
    elligent
    -0.81
    TPP
    -0.80
    NAT
    -0.80
    ealous
    -0.80
    POSITIVE LOGITS
     surfaces
    1.16
     cheeks
    0.97
     surface
    0.94
     walls
    0.93
     soaked
    0.91
     linen
    0.89
     sidewalks
    0.89
     bones
    0.89
     pavement
    0.89
     scratched
    0.88
    Activations Density 0.102%

    No Known Activations