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. 11993
    Prev
    Next
    INDEX
    Explanations

    details related to urban development and construction projects

    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
    734
    +0.11
    0.5%
    459
    +0.10
    0.5%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    714
    +0.11
    0.03
    596
    +0.10
    0.04
    459
    +0.10
    0.04
    Negative Logits
     Virus
    -0.88
    ERROR
    -0.87
     blindly
    -0.81
     saliva
    -0.79
    errors
    -0.79
    20439
    -0.75
     CTRL
    -0.71
     grep
    -0.70
     plagiar
    -0.70
     tainted
    -0.69
    POSITIVE LOGITS
     landsc
    1.24
     redevelop
    1.17
     amenities
    1.17
     seating
    1.16
     redevelopment
    1.14
     residences
    1.08
     adjoining
    1.08
     architectural
    1.07
     plaza
    1.06
     exterior
    1.05
    Activations Density 0.371%

    No Known Activations