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 49152
    5. 8-RES_FS49152-JB
    6. 26139
    Prev
    Next
    INDEX
    Explanations

    dates and timestamps 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_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.11
    0.5%
    76
    +0.10
    0.5%
    98
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.11
    0.02
    521
    +0.10
    0.01
    18
    +0.09
    0.01
    Negative Logits
     pregn
    -0.70
     parap
    -0.69
     fortun
    -0.67
    accompanied
    -0.64
     indisp
    -0.64
    andise
    -0.63
     unaccount
    -0.63
     strugg
    -0.62
    along
    -0.62
    å¸
    -0.61
    POSITIVE LOGITS
     Tweet
    0.80
     Invalid
    0.80
    utterstock
    0.70
     [+]
    0.68
    arth
    0.67
    ographics
    0.65
    raint
    0.63
    Invalid
    0.62
    urrencies
    0.62
     09
    0.62
    Activations Density 0.025%

    No Known Activations