© 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. 9350
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal activities and legal procedures

    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
    628
    +0.10
    0.5%
    131
    +0.10
    0.5%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.10
    0.03
    357
    +0.10
    0.03
    451
    +0.09
    0.02
    Negative Logits
    Reviewer
    -0.84
    natureconservancy
    -0.66
    Tokens
    -0.66
     wat
    -0.64
     Sho
    -0.63
    soDeliveryDate
    -0.62
     Nobel
    -0.62
     contrace
    -0.61
     Doodle
    -0.60
     Scandinav
    -0.60
    POSITIVE LOGITS
     felony
    1.42
     misdemeanor
    1.35
     indictment
    1.27
     misdem
    1.26
     indict
    1.25
     offences
    1.19
     aggravated
    1.19
    criminal
    1.15
     offenses
    1.15
     criminal
    1.15
    Activations Density 0.093%

    No Known Activations