© 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. 27526
    Prev
    Next
    INDEX
    Explanations

    names or references to people

    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
    745
    +0.11
    0.5%
    135
    +0.11
    0.5%
    471
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.07
    232
    +0.11
    0.07
    314
    +0.11
    0.00
    Negative Logits
     acronym
    -0.73
     outdoors
    -0.72
     Chaser
    -0.69
     clipboard
    -0.68
     Paste
    -0.65
     vertically
    -0.64
     ultras
    -0.64
     initials
    -0.63
     Alchemist
    -0.63
     unchanged
    -0.63
    POSITIVE LOGITS
    rington
    1.24
    riott
    1.23
    baugh
    1.21
    reau
    1.17
    zman
    1.14
    raud
    1.13
    rone
    1.11
    heny
    1.10
    zel
    1.08
    rell
    1.07
    Activations Density 0.545%

    No Known Activations