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 24576
    5. 8-RES_FS24576-JB
    6. 11457
    Prev
    Next
    INDEX
    Explanations

    legislation-related terms and actions, including bills, laws, and penalties

    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
    529
    +0.11
    0.5%
    123
    +0.10
    0.5%
    203
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    529
    +0.11
    0.05
    421
    +0.10
    0.04
    123
    +0.10
    0.04
    Negative Logits
     Passion
    -0.89
    angelo
    -0.67
     infinity
    -0.65
     virt
    -0.64
     Zeit
    -0.63
     Phantom
    -0.63
     Stronghold
    -0.62
     psyche
    -0.61
     Prophet
    -0.60
     loves
    -0.60
    POSITIVE LOGITS
     protections
    1.03
    osponsors
    1.01
     decriminal
    0.94
     repealed
    0.91
     exemptions
    0.90
     federally
    0.89
     penalties
    0.88
     loopholes
    0.87
     repealing
    0.86
     unconstitutional
    0.86
    Activations Density 0.336%

    No Known Activations