© 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. 7854
    Prev
    Next
    INDEX
    Explanations

    direct speech examples containing the word 'just'

    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
    106
    +0.12
    0.6%
    508
    +0.11
    0.5%
    633
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    633
    +0.12
    0.05
    106
    +0.11
    0.04
    498
    +0.10
    0.04
    Negative Logits
    ccording
    -0.71
     Palestin
    -0.69
     challeng
    -0.66
     Archdemon
    -0.64
     subsequ
    -0.63
     holiest
    -0.62
    der
    -0.61
     Nurs
    -0.58
     supervised
    -0.58
     PLUS
    -0.58
    POSITIVE LOGITS
    ifiable
    1.29
    ifications
    1.16
    ification
    0.98
    ify
    0.97
    ified
    0.96
    if
    0.94
     ignore
    0.90
    ifi
    0.89
     plain
    0.86
    ifiers
    0.84
    Activations Density 0.072%

    No Known Activations