© 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 EvalsExportsAPI 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. 28405
    Prev
    Next
    INDEX
    Explanations

    references to collections or collages

    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
    649
    +0.09
    0.4%
    395
    +0.09
    0.4%
    619
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.09
    -0.00
    232
    +0.09
    0.02
    288
    +0.09
    0.03
    Negative Logits
    iPhone
    -0.61
     laptops
    -0.60
    Ô
    -0.59
     Rack
    -0.58
     affidavit
    -0.58
     laptop
    -0.55
    quist
    -0.55
    ¯¯¯¯¯¯¯¯
    -0.54
     blockers
    -0.54
     Goals
    -0.54
    POSITIVE LOGITS
    oned
    1.01
    iding
    0.96
    oqu
    0.96
    imated
    0.94
    uded
    0.89
    uding
    0.86
    oning
    0.84
    oidal
    0.81
    imating
    0.80
    ocated
    0.77
    Activations Density 0.137%

    No Known Activations