© 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. 4822
    Prev
    Next
    INDEX
    Explanations

    links or URLs within text

    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
    222
    +0.12
    0.6%
    167
    +0.12
    0.6%
    314
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.12
    0.02
    222
    +0.12
    0.02
    129
    +0.11
    0.02
    Negative Logits
     merry
    -0.70
    ILLE
    -0.60
    perty
    -0.59
     Kear
    -0.58
     Advocate
    -0.58
     reper
    -0.57
     Woods
    -0.56
     Wildcats
    -0.55
    zza
    -0.54
     gratification
    -0.54
    POSITIVE LOGITS
    ening
    1.54
    ener
    1.33
    eners
    1.26
    ened
    1.13
    enable
    1.10
    ings
    1.04
    erv
    1.00
    uce
    1.00
    ing
    0.99
    ens
    0.90
    Activations Density 0.024%

    No Known Activations