© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 27036
    Prev
    Next
    INDEX
    Explanations

    references to legislative acts and historical legal frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    524
    +0.11
    0.5%
    759
    +0.10
    0.5%
    758
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    524
    +0.11
    0.02
    547
    +0.10
    0.01
    224
    +0.10
    0.01
    Negative Logits
    uckland
    -0.74
     Wally
    -0.66
    =~=~
    -0.65
     Mong
    -0.64
     Perth
    -0.64
    uton
    -0.61
     Indones
    -0.61
     Indigo
    -0.60
    Intern
    -0.59
    Fest
    -0.59
    POSITIVE LOGITS
     Amendments
    0.95
     ([
    0.85
     enacted
    0.76
     promulg
    0.76
     ("
    0.75
     repealed
    0.74
     <<
    0.74
     Compliance
    0.73
     authored
    0.73
     Regulations
    0.73
    Activations Density 0.046%

    No Known Activations