© 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. 27415
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating relationships or connections

    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
    536
    +0.12
    0.6%
    643
    +0.12
    0.5%
    362
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.12
    0.16
    362
    +0.12
    0.12
    669
    +0.10
    0.10
    Negative Logits
    RAW
    -0.80
     virtually
    -0.77
    chwitz
    -0.75
     nearly
    -0.73
     whereas
    -0.71
     preferably
    -0.71
     moreover
    -0.70
     MUCH
    -0.70
     however
    -0.70
     throughout
    -0.69
    POSITIVE LOGITS
     luck
    0.66
     instinct
    0.65
    erous
    0.64
     charm
    0.63
    education
    0.60
     curiosity
    0.58
    ured
    0.56
     imagination
    0.56
     ceremonial
    0.55
     theory
    0.55
    Activations Density 1.707%

    No Known Activations