© 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. 31938
    Prev
    Next
    INDEX
    Explanations

    references to significant buildings and structures

    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
    35
    +0.13
    0.6%
    497
    +0.12
    0.5%
    275
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.03
    146
    +0.12
    0.01
    275
    +0.11
    0.01
    Negative Logits
    ournals
    -0.75
    ero
    -0.74
    stro
    -0.74
    asia
    -0.73
    ery
    -0.72
    ouse
    -0.72
    ering
    -0.70
    Äĩ
    -0.69
    doors
    -0.69
    okers
    -0.69
    POSITIVE LOGITS
     sidx
    0.73
    ãĤ¼ãĤ¦ãĤ¹
    0.70
     1936
    0.69
    ptives
    0.68
    idates
    0.67
    idated
    0.66
     rall
    0.65
     Ruler
    0.65
    Fal
    0.64
     Hik
    0.64
    Activations Density 0.083%

    No Known Activations