© 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. 18917
    Prev
    Next
    INDEX
    Explanations

    phrases related to policies, procedures, and legal terms

    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
    679
    +0.13
    0.6%
    398
    +0.10
    0.4%
    514
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.13
    0.05
    393
    +0.10
    0.05
    328
    +0.09
    0.04
    Negative Logits
    Jr
    -0.78
    usercontent
    -0.77
    ooked
    -0.73
     Females
    -0.71
    imbabwe
    -0.71
    urious
    -0.70
    osaurs
    -0.69
    gyn
    -0.69
    kees
    -0.69
    wreck
    -0.69
    POSITIVE LOGITS
     procedures
    1.29
     regulations
    1.25
     practices
    1.17
     protocols
    1.11
     procedure
    1.11
     tactics
    1.11
     Procedures
    1.07
     Regulations
    1.06
     regulation
    1.06
     timet
    1.06
    Activations Density 0.265%

    No Known Activations