© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12399
    Prev
    Next
    INDEX
    Explanations

    references to police responses and investigations

    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
    745
    +0.10
    0.5%
    481
    +0.10
    0.5%
    628
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.06
    608
    +0.10
    0.06
    385
    +0.10
    0.05
    Negative Logits
     congr
    -0.80
    gebra
    -0.75
     metaphor
    -0.66
    HTML
    -0.66
    Phys
    -0.65
    xual
    -0.64
    TPP
    -0.64
    fried
    -0.64
    JP
    -0.64
     experimented
    -0.63
    POSITIVE LOGITS
     perimeter
    0.96
     premises
    0.93
     vicinity
    0.89
    tnc
    0.84
     nearby
    0.83
     periphery
    0.82
     area
    0.79
     outskirts
    0.79
     downtown
    0.76
     rooft
    0.75
    Activations Density 0.368%

    No Known Activations