© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29902
    Prev
    Next
    INDEX
    Explanations

    phrases indicating similarities or identical features

    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
    1
    +0.11
    0.5%
    539
    +0.10
    0.5%
    418
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    514
    +0.11
    0.03
    507
    +0.10
    0.04
    296
    +0.09
    0.03
    Negative Logits
    veland
    -0.67
     Sev
    -0.66
    achment
    -0.65
    capital
    -0.63
     trusted
    -0.63
    mberg
    -0.61
    nos
    -0.60
    hement
    -0.59
     distraction
    -0.59
     Guid
    -0.57
    POSITIVE LOGITS
     twins
    1.01
    lihood
    0.94
    ively
    0.92
    icut
    0.76
     except
    0.75
     enough
    0.73
    ially
    0.71
     chemically
    0.69
    ingly
    0.69
    etrical
    0.68
    Activations Density 0.259%

    No Known Activations