© 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. 8-RES_POST_32K-OAI
    11. 7989
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly related to some form of measurement or identification

    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
    7
    +0.13
    0.6%
    361
    +0.09
    0.4%
    284
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.02
    472
    +0.09
    0.01
    7
    +0.09
    0.02
    Negative Logits
    berman
    -0.87
    glers
    -0.77
    ãħĭ
    -0.74
     assum
    -0.72
    ittle
    -0.71
    imoto
    -0.69
    elman
    -0.67
     Kush
    -0.67
    lein
    -0.66
    gom
    -0.66
    POSITIVE LOGITS
     Bride
    0.78
    dB
    0.71
    hus
    0.70
    ŃĶ
    0.67
    ĵĺ
    0.67
    sylvania
    0.66
    olves
    0.65
    595
    0.64
    66
    0.64
    80
    0.63
    Activations Density 0.089%

    No Known Activations