© 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. 27350
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly colons and semicolons, indicating lists or separations in text

    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
    +0.15
    0.7%
    314
    +0.13
    0.6%
    442
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.15
    -0.00
    284
    +0.13
    0.01
    304
    +0.11
    0.02
    Negative Logits
     hasht
    -0.64
     conversions
    -0.61
     immersion
    -0.60
     Bund
    -0.59
     ado
    -0.58
     visitation
    -0.58
    netflix
    -0.58
     neut
    -0.58
     flats
    -0.58
     Nug
    -0.57
    POSITIVE LOGITS
    D
    1.23
    P
    1.18
    rolley
    1.07
    DD
    1.04
    O
    1.02
    -(
    1.02
    OX
    1.01
    Ps
    1.00
    DP
    1.00
    DI
    0.97
    Activations Density 0.228%

    No Known Activations