© 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 49152
    9. 8-RES_FS49152-JB
    11. 37247
    Prev
    Next
    INDEX
    Explanations

    phrases related to road safety and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    87
    +0.22
    1.1%
    756
    +0.15
    0.8%
    459
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.22
    -0.01
    87
    +0.15
    -0.02
    283
    +0.09
    0.01
    Negative Logits
    NetMessage
    -0.79
    Hide
    -0.67
    illance
    -0.66
     Cosponsors
    -0.64
    OWN
    -0.61
     Everywhere
    -0.60
     Detect
    -0.58
    olitical
    -0.56
    ophen
    -0.56
     UFOs
    -0.54
    POSITIVE LOGITS
     averages
    0.96
     estimate
    0.93
     averaged
    0.92
     counting
    0.85
     estimates
    0.84
     totals
    0.81
     averaging
    0.81
     accounted
    0.80
     multiplied
    0.80
     dwar
    0.78
    Activations Density 0.415%

    No Known Activations