© 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. 12304
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific model mentioned several times in the document

    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
    420
    +0.11
    0.5%
    706
    +0.09
    0.4%
    493
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.02
    420
    +0.09
    0.02
    232
    +0.09
    0.02
    Negative Logits
    etheless
    -0.70
     guiActiveUnfocused
    -0.69
    IONS
    -0.67
    ION
    -0.66
     IMAGES
    -0.66
     Gateway
    -0.65
    IBLE
    -0.63
    åħī
    -0.63
    70710
    -0.60
     totality
    -0.58
    POSITIVE LOGITS
    eling
    1.16
    pler
    1.11
    ptic
    1.09
    SPA
    1.07
    lder
    1.06
    bye
    1.02
    ppel
    1.01
    pper
    1.01
    ck
    1.00
    aton
    0.99
    Activations Density 0.016%

    No Known Activations