© 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. 16465
    Prev
    Next
    INDEX
    Explanations

    tech-related terms and information

    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
    393
    +0.14
    0.6%
    0
    +0.11
    0.5%
    724
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    +0.14
    0.08
    484
    +0.11
    0.07
    703
    +0.09
    0.06
    Negative Logits
    osta
    -0.76
    lled
    -0.74
    edia
    -0.73
    othal
    -0.73
    iless
    -0.73
    icz
    -0.68
    Spoiler
    -0.68
    west
    -0.67
    lished
    -0.67
     Arkham
    -0.66
    POSITIVE LOGITS
     thereby
    1.04
     consequently
    0.98
     hence
    0.89
     thus
    0.86
     Practices
    0.79
     therefore
    0.78
     accessories
    0.78
     practices
    0.77
     secondly
    0.75
     technologies
    0.74
    Activations Density 0.341%

    No Known Activations