© 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. 1691
    Prev
    Next
    INDEX
    Explanations

    information related to police reports and criminal activities

    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
    373
    +0.13
    0.6%
    133
    +0.10
    0.4%
    604
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.13
    0.05
    448
    +0.10
    0.04
    133
    +0.09
    0.04
    Negative Logits
    obyl
    -1.06
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.87
    NetMessage
    -0.81
    osate
    -0.74
    ennial
    -0.70
    oliberal
    -0.69
    itous
    -0.68
     monopol
    -0.67
    ãĥĺ
    -0.65
    culosis
    -0.65
    POSITIVE LOGITS
     sources
    1.10
     prosecutors
    1.01
     affidavit
    0.92
     spokeswoman
    0.92
     eyewitness
    0.90
     affidav
    0.88
     spokesman
    0.87
     police
    0.84
     testimony
    0.83
     reports
    0.83
    Activations Density 0.208%

    No Known Activations