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. 26163
    Prev
    Next
    INDEX
    Explanations

    references to articles

    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
    679
    +0.10
    0.5%
    360
    +0.10
    0.5%
    114
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.10
    0.02
    452
    +0.10
    0.02
    175
    +0.10
    0.02
    Negative Logits
    cffff
    -0.87
    cffffcc
    -0.82
    pter
    -0.69
     Nadu
    -0.68
    NetMessage
    -0.68
    cles
    -0.67
    IER
    -0.66
     bandits
    -0.65
    ²¾
    -0.63
     Guard
    -0.62
    POSITIVE LOGITS
    meal
    1.01
     published
    0.96
     articles
    0.93
    orial
    0.80
     detailing
    0.80
    udo
    0.80
     authored
    0.79
     Articles
    0.79
     mentioning
    0.77
     editor
    0.77
    Activations Density 0.021%

    No Known Activations