© 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 EvalsExportsinterp-engineNEWAPI 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. 15682
    Prev
    Next
    INDEX
    Explanations

    information related to demographic statistics and events or competitions happening within a specific community

    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
    410
    +0.13
    0.6%
    61
    +0.09
    0.4%
    404
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.13
    0.03
    362
    +0.09
    0.03
    467
    +0.09
    0.02
    Negative Logits
    Newsletter
    -0.91
    lass
    -0.84
    tick
    -0.80
    las
    -0.80
    ares
    -0.79
    jen
    -0.77
    hip
    -0.77
    bucks
    -0.76
    witch
    -0.75
    habi
    -0.74
    POSITIVE LOGITS
     exception
    1.53
     exceptions
    1.41
     caveat
    1.34
     emphasis
    1.27
     consequ
    1.21
     implication
    1.20
     attendant
    1.18
     notable
    1.13
     resultant
    1.08
     caveats
    1.08
    Activations Density 0.153%

    No Known Activations