© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 27727
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and their associated data

    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
    67
    +0.10
    0.5%
    225
    +0.10
    0.5%
    31
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.10
    0.10
    409
    +0.10
    0.07
    568
    +0.09
    0.06
    Negative Logits
     Disneyland
    -0.76
    duino
    -0.74
    odka
    -0.73
    hz
    -0.73
    hetto
    -0.71
     mall
    -0.71
    zees
    -0.67
     Strongh
    -0.67
    iors
    -0.66
    twitch
    -0.65
    POSITIVE LOGITS
     PubMed
    1.59
     journals
    1.54
     citations
    1.52
     journal
    1.45
     manuscripts
    1.43
     citation
    1.37
     publications
    1.36
     Journals
    1.35
     manuscript
    1.35
    ournals
    1.34
    Activations Density 2.526%

    No Known Activations