© 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. 8701
    Prev
    Next
    INDEX
    Explanations

    terms related to temperature and environmental conditions

    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
    321
    +0.11
    0.5%
    57
    +0.11
    0.5%
    178
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.11
    0.02
    178
    +0.11
    0.02
    57
    +0.10
    0.02
    Negative Logits
    doms
    -0.82
    rahim
    -0.81
    ioned
    -0.77
    business
    -0.76
    fman
    -0.76
    lez
    -0.76
    vous
    -0.74
    enegger
    -0.74
    BACK
    -0.73
    legate
    -0.73
    POSITIVE LOGITS
     temperatures
    1.13
     extremes
    1.08
     temperature
    1.03
     gradient
    1.03
     fluctuations
    1.02
     anomalies
    0.93
     humidity
    0.89
    perature
    0.88
     readings
    0.88
     Fahrenheit
    0.87
    Activations Density 0.026%

    No Known Activations