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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11375
    Prev
    Next
    INDEX
    Explanations

    present participle verbs ending in 'ing'

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    447
    +0.20
    0.9%
    93
    +0.10
    0.5%
    391
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.20
    0.04
    461
    +0.10
    0.04
    343
    +0.10
    0.04
    Negative Logits
    Rust
    -0.94
    Rh
    -0.93
    ccoli
    -0.81
    Ô
    -0.79
    Oracle
    -0.75
    akable
    -0.75
    thens
    -0.74
    akespe
    -0.74
    Slow
    -0.73
    erving
    -0.73
    POSITIVE LOGITS
     program
    0.96
     products
    0.94
     programme
    0.93
     product
    0.93
     platform
    0.91
     system
    0.90
     device
    0.90
     logo
    0.89
     programs
    0.86
     phenomenon
    0.86
    Activations Density 0.260%

    No Known Activations