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

    Neuronpedia

    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. 19456
    Prev
    Next
    INDEX
    Explanations

    locations or points of interest specified in terms of coordinates or distance

    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
    +0.15
    0.8%
    160
    +0.13
    0.7%
    17
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.15
    0.02
    160
    +0.13
    0.03
    173
    +0.11
    0.02
    Negative Logits
     lax
    -0.70
     Zeit
    -0.69
     entitlement
    -0.68
     privilege
    -0.65
     Sinai
    -0.65
     omission
    -0.65
     Boko
    -0.64
     Nost
    -0.63
     inaction
    -0.63
     Starr
    -0.63
    POSITIVE LOGITS
    approximately
    1.09
    including
    0.94
    formerly
    0.94
    more
    0.93
    almost
    0.92
    rough
    0.91
    yards
    0.91
    although
    0.90
    mostly
    0.90
    later
    0.89
    Activations Density 0.031%

    No Known Activations