© 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. 27186
    Prev
    Next
    INDEX
    Explanations

    references to problems, issues, or notable observations in various contexts

    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
    314
    +0.12
    0.5%
    433
    +0.10
    0.5%
    745
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.12
    0.12
    433
    +0.10
    0.10
    696
    +0.10
    0.11
    Negative Logits
     Weston
    -0.66
     Atkins
    -0.63
    alus
    -0.61
     Samar
    -0.60
     Watkins
    -0.60
     Fiat
    -0.59
     Lima
    -0.58
     Giov
    -0.58
     Volunte
    -0.58
     Shelby
    -0.57
    POSITIVE LOGITS
    *:
    1.34
    »
    1.33
    \)
    1.31
    ãĢij
    1.29
    *)
    1.29
    *.
    1.27
    >:
    1.24
    *
    1.23
    âĢ¢
    1.18
    ***
    1.16
    Activations Density 4.705%

    No Known Activations