© 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. 27137
    Prev
    Next
    INDEX
    Explanations

    words related to improvement and optimality

    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
    331
    +0.14
    0.6%
    3
    +0.12
    0.5%
    140
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.14
    0.04
    140
    +0.12
    0.04
    331
    +0.11
    0.03
    Negative Logits
     impossibility
    -0.67
     Quit
    -0.63
     Creep
    -0.60
     circumcision
    -0.60
     wee
    -0.59
     Freak
    -0.59
     Lots
    -0.58
     miracle
    -0.58
     Mehran
    -0.58
     Lot
    -0.57
    POSITIVE LOGITS
    resents
    0.97
    rehend
    0.97
     represent
    0.95
     represented
    0.92
     represents
    0.92
     understand
    0.92
     encaps
    0.92
     suited
    0.92
     reflects
    0.91
     comprehend
    0.90
    Activations Density 0.610%

    No Known Activations