Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11240
    Prev
    Next
    INDEX
    Explanations

    mentions of injuries and related terms such as accidents

    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
    274
    +0.10
    0.5%
    132
    +0.10
    0.5%
    762
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.10
    0.03
    132
    +0.10
    0.02
    114
    +0.10
    0.02
    Negative Logits
    tz
    -0.76
    zee
    -0.73
    arten
    -0.70
    ullivan
    -0.70
    ramid
    -0.69
    adian
    -0.68
    arity
    -0.67
    zees
    -0.66
    zsche
    -0.66
    esters
    -0.65
    POSITIVE LOGITS
     inflicted
    1.31
     incurred
    1.13
     sustained
    1.05
     suffered
    1.02
    letal
    0.91
     injuries
    0.89
     inflic
    0.88
     caused
    0.87
     victims
    0.81
     injury
    0.79
    Activations Density 0.037%

    No Known Activations