© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19569
    Prev
    Next
    INDEX
    Explanations

    descriptions of places, particularly vibrant or expressive ones

    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
    495
    +0.14
    0.6%
    447
    +0.13
    0.6%
    651
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.14
    0.04
    651
    +0.13
    0.03
    288
    +0.12
    0.04
    Negative Logits
     Fighters
    -0.73
    sels
    -0.66
     Friendly
    -0.64
     Lover
    -0.61
     occasional
    -0.61
    Friend
    -0.59
    favorite
    -0.59
     Extrem
    -0.59
    reetings
    -0.57
    odan
    -0.56
    POSITIVE LOGITS
     except
    0.99
     revolves
    0.85
     imaginable
    0.79
     Including
    0.77
    代
    0.75
    âĶĢâĶĢ
    0.74
     including
    0.74
    bang
    0.73
     depended
    0.70
     catalogue
    0.68
    Activations Density 0.133%

    No Known Activations