© 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. 29674
    Prev
    Next
    INDEX
    Explanations

    instances of brackets and parentheses in the text

    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
    442
    +0.16
    0.7%
    102
    +0.13
    0.6%
    160
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.16
    0.08
    102
    +0.13
    0.07
    442
    +0.12
    0.05
    Negative Logits
     brim
    -0.86
     cog
    -0.79
     flex
    -0.77
     tremend
    -0.76
     horizon
    -0.75
     imperfect
    -0.74
     fiat
    -0.73
     unsupported
    -0.72
     deserts
    -0.71
     Cth
    -0.71
    POSITIVE LOGITS
    sic
    1.43
    Wednesday
    1.30
    Tuesday
    1.27
    President
    1.27
    Democratic
    1.25
    Thursday
    1.21
    Obama
    1.19
    Department
    1.18
    Park
    1.17
    â̦)
    1.17
    Activations Density 0.172%

    No Known Activations