© 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. 10-RES_POST_32K-OAI
    11. 29920
    Prev
    Next
    INDEX
    Explanations

    dates and timestamps

    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
    497
    +0.12
    0.6%
    746
    +0.08
    0.4%
    306
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.12
    -0.04
    266
    +0.08
    0.08
    480
    +0.08
    0.05
    Negative Logits
     resemb
    -0.72
     sag
    -0.68
     recourse
    -0.64
     multif
    -0.63
     gib
    -0.60
     exha
    -0.60
     vanity
    -0.60
     bene
    -0.59
     vig
    -0.59
     schemes
    -0.59
    POSITIVE LOGITS
     08
    0.79
     09
    0.75
     02
    0.74
     05
    0.74
     04
    0.74
     07
    0.73
     REUTERS
    0.73
     06
    0.73
    .).
    0.73
     03
    0.73
    Activations Density 0.888%

    No Known Activations