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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5922
    Prev
    Next
    INDEX
    Explanations

    mentions of key individuals in discussions of healthcare and legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    172
    +0.13
    0.6%
    31
    +0.12
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.03
    232
    +0.12
    0.03
    326
    +0.11
    0.02
    Negative Logits
    Ń·
    -0.72
    DX
    -0.70
    wark
    -0.65
     Million
    -0.64
     Emir
    -0.63
     chest
    -0.63
     Speedway
    -0.61
    comings
    -0.61
     Mariners
    -0.60
     Sabha
    -0.59
    POSITIVE LOGITS
    iaries
    0.98
    enberg
    0.98
    unci
    0.97
    unciation
    0.97
    ouncing
    0.90
    eling
    0.89
    el
    0.89
    els
    0.88
    aches
    0.87
    ounce
    0.83
    Activations Density 0.100%

    No Known Activations