© 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. 22730
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or entities, particularly ones associated with the term "Mon."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    497
    +0.13
    0.6%
    640
    +0.13
    0.6%
    710
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    710
    +0.13
    0.02
    52
    +0.13
    0.02
    694
    +0.12
    0.02
    Negative Logits
     Norn
    -0.82
    FUL
    -0.79
    ACTED
    -0.77
    REE
    -0.76
    IBLE
    -0.72
    OHN
    -0.67
    ATING
    -0.66
    ATOR
    -0.65
    enegger
    -0.64
    éĹĺ
    -0.64
    POSITIVE LOGITS
    itored
    1.24
    olith
    1.24
    stros
    1.18
    astery
    1.13
    olithic
    1.13
    opoly
    1.12
    soon
    1.09
    ographs
    1.04
    ograph
    1.03
    roe
    1.02
    Activations Density 0.014%

    No Known Activations