© 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. 20887
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental influences, genetic factors, and external forces that impact variables or models

    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
    53
    +0.13
    0.6%
    27
    +0.11
    0.5%
    408
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.13
    0.06
    27
    +0.11
    0.04
    53
    +0.11
    0.04
    Negative Logits
    sterdam
    -0.95
    ploma
    -0.81
    ocry
    -0.80
    ACP
    -0.79
    inis
    -0.76
    NAS
    -0.75
    phabet
    -0.75
    iversary
    -0.75
    enda
    -0.75
    byter
    -0.73
    POSITIVE LOGITS
     factors
    1.46
     intervened
    1.15
     influences
    1.09
     influencing
    1.08
     variables
    1.05
     affecting
    1.05
     Factors
    1.03
     predis
    1.00
     exacerbated
    1.00
     impacting
    0.97
    Activations Density 0.310%

    No Known Activations