© 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. 32175
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of places and 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
    373
    +0.13
    0.6%
    392
    +0.10
    0.5%
    20
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.13
    0.02
    567
    +0.10
    0.01
    139
    +0.10
    0.03
    Negative Logits
     marqu
    -0.67
    olor
    -0.67
    onne
    -0.63
     eleph
    -0.62
    ME
    -0.59
    Ell
    -0.59
    omever
    -0.58
    heet
    -0.57
    oler
    -0.57
     ect
    -0.57
    POSITIVE LOGITS
    's
    0.71
     Nanto
    0.70
    're
    0.62
     Likes
    0.61
     Gets
    0.60
     Saunders
    0.59
    istic
    0.58
    ics
    0.58
    ches
    0.57
    ski
    0.57
    Activations Density 0.409%

    No Known Activations