Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23171
    Prev
    Next
    INDEX
    Explanations

    dates related to events or mentions in the text

    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
    240
    +0.13
    0.6%
    385
    +0.10
    0.5%
    301
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.13
    0.04
    301
    +0.10
    0.03
    240
    +0.10
    0.03
    Negative Logits
    fman
    -0.83
    kus
    -0.71
    chers
    -0.69
    ps
    -0.69
    cher
    -0.69
    ggle
    -0.68
    cius
    -0.68
    ventus
    -0.67
    ching
    -0.67
    king
    -0.67
    POSITIVE LOGITS
     Surprise
    1.11
    fair
    0.84
     2014
    0.84
     2015
    0.81
    avia
    0.80
     2012
    0.80
     2013
    0.79
     2017
    0.79
     2016
    0.77
    OB
    0.77
    Activations Density 0.018%

    No Known Activations