© 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. 18879
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues or environmental crimes

    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
    490
    +0.12
    0.5%
    314
    +0.11
    0.5%
    360
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.12
    0.02
    82
    +0.11
    0.02
    144
    +0.09
    0.02
    Negative Logits
     Flavoring
    -0.81
     Schwar
    -0.66
     Afgh
    -0.65
     Journey
    -0.63
     Glob
    -0.61
     Patriot
    -0.61
     rendition
    -0.61
     ultraviolet
    -0.59
     Kut
    -0.59
    )=(
    -0.59
    POSITIVE LOGITS
    inators
    1.30
    inator
    1.26
    uting
    1.21
    uted
    1.13
    uter
    1.11
    inating
    1.09
    ution
    1.09
    inated
    1.08
    uters
    1.05
    arding
    1.03
    Activations Density 0.017%

    No Known Activations