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. 46033
    Prev
    Next
    INDEX
    Explanations

    the word "App" 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_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
    7
    +0.11
    0.5%
    276
    +0.10
    0.5%
    360
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.11
    0.01
    623
    +0.10
    0.02
    360
    +0.10
    0.02
    Negative Logits
    terday
    -0.72
    Reloaded
    -0.71
     Spectrum
    -0.68
     caucus
    -0.63
     tort
    -0.62
     knot
    -0.62
     steroids
    -0.61
    EStreamFrame
    -0.60
     conce
    -0.60
     cigars
    -0.59
    POSITIVE LOGITS
    alach
    1.50
    ointment
    1.45
    reciation
    1.39
    earing
    1.39
    eared
    1.37
    arent
    1.34
    rentices
    1.33
    rox
    1.33
    ropri
    1.33
    earance
    1.33
    Activations Density 0.013%

    No Known Activations