© 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. 31663
    Prev
    Next
    INDEX
    Explanations

    copyright and publication-related terms

    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
    373
    +0.18
    0.8%
    598
    +0.10
    0.5%
    497
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    309
    +0.18
    0.01
    627
    +0.10
    0.00
    530
    +0.10
    0.01
    Negative Logits
    otin
    -0.73
    xual
    -0.72
     stride
    -0.71
    EStreamFrame
    -0.71
     pronouns
    -0.70
     resettlement
    -0.67
     hashing
    -0.66
     raids
    -0.66
     partying
    -0.66
     nuts
    -0.65
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.86
    Jean
    0.83
    George
    0.79
    Howard
    0.78
    William
    0.76
    Hart
    0.73
    Champ
    0.73
     Mai
    0.71
    Beck
    0.71
    Charles
    0.71
    Activations Density 0.088%

    No Known Activations