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. 43132
    Prev
    Next
    INDEX
    Explanations

    terms related to governance and political structures

    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
    447
    +0.18
    0.8%
    481
    +0.13
    0.6%
    459
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.07
    459
    +0.13
    0.04
    210
    +0.12
    0.03
    Negative Logits
    otal
    -0.76
    akespeare
    -0.66
    anuts
    -0.62
    indu
    -0.58
     Feather
    -0.58
    aunder
    -0.58
    ilts
    -0.57
    enged
    -0.57
    urbed
    -0.57
    ealous
    -0.56
    POSITIVE LOGITS
     hires
    0.79
     arrivals
    0.78
     paradigm
    0.73
     entrants
    0.70
     additions
    0.69
     roadmap
    0.69
     hire
    0.69
     iteration
    0.68
     architectures
    0.68
     Dino
    0.64
    Activations Density 0.284%

    No Known Activations