© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19800
    Prev
    Next
    INDEX
    Explanations

    terms related to fossil fuels and energy policy

    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
    288
    +0.19
    0.9%
    290
    +0.12
    0.6%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    290
    +0.19
    0.02
    288
    +0.12
    0.01
    456
    +0.09
    0.01
    Negative Logits
    annis
    -0.78
    ournal
    -0.74
    yang
    -0.70
    arta
    -0.69
     Synd
    -0.68
    ansky
    -0.67
    reads
    -0.67
    mble
    -0.66
    yk
    -0.65
    amber
    -0.64
    POSITIVE LOGITS
     fuels
    1.24
     fuel
    1.11
    ized
    1.10
    fuel
    1.00
    ifer
    0.96
    ization
    0.95
     footprints
    0.93
     fossil
    0.90
    itions
    0.88
    ised
    0.88
    Activations Density 0.009%

    No Known Activations