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. 41215
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations and affiliations

    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
    481
    +0.15
    0.7%
    629
    +0.12
    0.5%
    732
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.15
    0.04
    752
    +0.12
    0.05
    693
    +0.10
    0.04
    Negative Logits
    rive
    -0.78
     retali
    -0.71
    ELF
    -0.70
    EMS
    -0.70
     efficacy
    -0.68
     takedown
    -0.67
     stopp
    -0.67
     destruct
    -0.67
     pause
    -0.65
     reversal
    -0.65
    POSITIVE LOGITS
     suburb
    1.00
     Heights
    0.95
     suburbs
    0.87
    hattan
    0.81
     County
    0.80
     Province
    0.77
     countryside
    0.77
    shire
    0.76
     Township
    0.76
     obscurity
    0.73
    Activations Density 0.163%

    No Known Activations