© 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. 5793
    Prev
    Next
    INDEX
    Explanations

    references to various forms of pills or related concepts

    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
    35
    +0.13
    0.6%
    526
    +0.13
    0.6%
    659
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.02
    35
    +0.13
    0.01
    659
    +0.13
    0.01
    Negative Logits
    REDACTED
    -0.74
     Cosponsors
    -0.72
    worldly
    -0.70
    elist
    -0.70
    auga
    -0.67
     quo
    -0.66
     Bucc
    -0.66
     EntityItem
    -0.62
     Giuliani
    -0.61
    ////////////////
    -0.61
    POSITIVE LOGITS
    ows
    1.30
    aging
    1.19
    oried
    1.19
    ager
    1.07
    agers
    1.03
    ars
    0.97
    iard
    0.96
    ard
    0.95
    agra
    0.95
    aged
    0.95
    Activations Density 0.058%

    No Known Activations