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 768
    5. 8-RES_FS768-JB
    6. 428
    Prev
    Next
    INDEX
    Explanations

    references to early time periods or beginnings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    132
    +0.11
    0.5%
    603
    +0.10
    0.4%
    746
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.11
    0.09
    746
    +0.10
    0.04
    99
    +0.10
    0.06
    Negative Logits
    utenberg
    -0.80
    edIn
    -0.77
    ICLE
    -0.72
     Pwr
    -0.69
    ikk
    -0.66
    atism
    -0.64
    roma
    -0.64
    ittee
    -0.63
    lde
    -0.63
    alach
    -0.62
    POSITIVE LOGITS
     mornings
    0.99
     morning
    0.99
     afternoon
    0.98
     twenties
    0.91
     evening
    0.86
     adop
    0.85
     stages
    0.84
     enough
    0.81
     versions
    0.80
     childhood
    0.78
    Activations Density 2.766%

    No Known Activations