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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 37129
    Prev
    Next
    INDEX
    Explanations

    issues related to spelling and pronunciation errors

    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
    366
    +0.12
    0.5%
    235
    +0.10
    0.4%
    683
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    607
    +0.12
    0.02
    103
    +0.10
    0.02
    235
    +0.10
    0.02
    Negative Logits
    illance
    -0.82
    adr
    -0.80
    etheus
    -0.79
    ramid
    -0.77
    ģĸ
    -0.76
    MRI
    -0.75
    galitarian
    -0.74
    ndra
    -0.73
    roxy
    -0.73
    emetery
    -0.73
    POSITIVE LOGITS
     spelling
    1.37
     pronunciation
    1.25
     phrases
    1.09
     words
    1.06
     pronouns
    1.06
     typo
    1.05
     alphabet
    1.03
     diction
    1.01
     initials
    1.01
     verbs
    1.01
    Activations Density 0.060%

    No Known Activations