© 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. 31108
    Prev
    Next
    INDEX
    Explanations

    instances of the word "until" followed by numerical references

    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
    529
    +0.11
    0.5%
    300
    +0.10
    0.5%
    218
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.11
    0.05
    471
    +0.10
    0.04
    572
    +0.10
    0.04
    Negative Logits
    ãĥķãĤ¡
    -0.79
    ardless
    -0.73
    abet
    -0.71
    fit
    -0.68
    Favorite
    -0.67
    keep
    -0.66
    ysis
    -0.65
    ãĥĨ
    -0.65
    ãĥīãĥ©
    -0.64
    estic
    -0.62
    POSITIVE LOGITS
     recently
    1.03
     weeks
    1.01
     much
    1.00
     months
    0.97
     decades
    0.95
     years
    0.92
    months
    0.81
     several
    0.79
     late
    0.78
     MUCH
    0.77
    Activations Density 0.330%

    No Known Activations