© 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. 5617
    Prev
    Next
    INDEX
    Explanations

    references to a central idea or figure within a discussion

    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
    537
    +0.11
    0.5%
    223
    +0.11
    0.5%
    365
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.01
    295
    +0.11
    0.01
    365
    +0.10
    0.01
    Negative Logits
    terday
    -0.72
     graded
    -0.69
    anguage
    -0.68
     Fang
    -0.66
     menstrual
    -0.65
     Fres
    -0.65
    ists
    -0.64
    lihood
    -0.63
     Leilan
    -0.62
     Grave
    -0.62
    POSITIVE LOGITS
    bub
    1.55
    bard
    1.29
    ris
    1.26
    lins
    1.16
    lot
    1.11
    bies
    1.01
    bie
    0.98
    bing
    0.98
    staff
    0.97
    rod
    0.97
    Activations Density 0.058%

    No Known Activations