© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5238
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "twenty" and its variations

    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
    314
    +0.12
    0.5%
    344
    +0.10
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.12
    0.03
    450
    +0.10
    0.02
    344
    +0.10
    0.03
    Negative Logits
    Activity
    -0.78
    Bank
    -0.66
    ULE
    -0.64
     Redemption
    -0.60
    ghai
    -0.59
     Caption
    -0.58
    etter
    -0.57
     Pwr
    -0.56
    GD
    -0.55
    GS
    -0.53
    POSITIVE LOGITS
     thousand
    1.16
    eenth
    1.11
    Eight
    0.92
    fold
    0.92
     Thousand
    0.91
    eight
    0.90
    ousand
    0.88
    four
    0.88
    something
    0.87
    teenth
    0.85
    Activations Density 0.044%

    No Known Activations