© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 27130
    Prev
    Next
    INDEX
    Explanations

    references to card game strategies or elements

    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
    728
    +0.10
    0.5%
    639
    +0.10
    0.5%
    110
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.06
    659
    +0.10
    0.04
    314
    +0.10
    -0.01
    Negative Logits
     fractions
    -0.75
     constitu
    -0.73
    qv
    -0.71
     charact
    -0.71
     arrang
    -0.71
    Characters
    -0.69
     prizes
    -0.69
     specials
    -0.68
     differe
    -0.68
     credits
    -0.68
    POSITIVE LOGITS
     Caller
    0.86
     Guide
    0.81
     Hub
    0.76
     Technician
    0.70
     Teacher
    0.70
    igator
    0.69
     Advocate
    0.68
     Revel
    0.68
     Tracker
    0.68
     Host
    0.68
    Activations Density 0.500%

    No Known Activations