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. 23650
    Prev
    Next
    INDEX
    Explanations

    instances of the word "recognize" and its variations in various contexts

    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
    288
    +0.12
    0.6%
    679
    +0.11
    0.5%
    654
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    654
    +0.12
    0.02
    1
    +0.11
    0.02
    161
    +0.10
    0.02
    Negative Logits
    stead
    -0.77
    quer
    -0.73
    ffield
    -0.73
    isher
    -0.71
    ionage
    -0.71
    etry
    -0.68
    hell
    -0.67
    isoft
    -0.67
    co
    -0.66
    ieri
    -0.65
    POSITIVE LOGITS
    enance
    0.92
    ledged
    0.91
    ibly
    0.89
    ibility
    0.79
     shortcomings
    0.75
     deficiencies
    0.74
    ably
    0.74
    phas
    0.73
     recognizing
    0.71
     distinctions
    0.68
    Activations Density 0.046%

    No Known Activations