© 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. 8-RES_POST_32K-OAI
    11. 6673
    Prev
    Next
    INDEX
    Explanations

    dates in April

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    638
    +0.12
    0.6%
    339
    +0.11
    0.5%
    388
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    707
    +0.12
    0.04
    306
    +0.11
    0.03
    310
    +0.09
    0.03
    Negative Logits
    atem
    -0.76
    enegger
    -0.73
    ted
    -0.72
    ancial
    -0.69
    lords
    -0.67
    reb
    -0.67
    ernandez
    -0.63
    swick
    -0.62
    ahime
    -0.61
    seeing
    -0.60
    POSITIVE LOGITS
     Fool
    1.01
    prints
    0.76
    nard
    0.74
    velop
    0.69
    onna
    0.67
    print
    0.65
    ctic
    0.65
    sburg
    0.63
    issance
    0.63
    flower
    0.63
    Activations Density 0.034%

    No Known Activations