© 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. 9040
    Prev
    Next
    INDEX
    Explanations

    details about laws or regulations related to specific issues or entities

    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
    480
    +0.34
    1.6%
    447
    +0.14
    0.7%
    670
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    516
    +0.34
    0.04
    575
    +0.14
    0.06
    567
    +0.10
    0.04
    Negative Logits
    çĶ°
    -0.69
     realise
    -0.68
    yssey
    -0.68
    BBC
    -0.65
     somew
    -0.64
     Carbuncle
    -0.64
     ;)
    -0.63
    tumblr
    -0.62
    ruary
    -0.62
    luck
    -0.62
    POSITIVE LOGITS
     unlawful
    0.95
     lawful
    0.95
     unconstitutional
    0.92
     lawfully
    0.91
     federally
    0.89
     voting
    0.85
     statewide
    0.84
     constitutionally
    0.84
     unlawfully
    0.84
     discretionary
    0.82
    Activations Density 0.647%

    No Known Activations