© 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. 26918
    Prev
    Next
    INDEX
    Explanations

    references to community engagement and social interactions

    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
    617
    +0.11
    0.5%
    509
    +0.10
    0.5%
    70
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.11
    0.16
    125
    +0.10
    0.10
    70
    +0.10
    0.17
    Negative Logits
     Plans
    -0.55
     Released
    -0.55
     [+
    -0.52
    stros
    -0.52
     convertible
    -0.52
    heid
    -0.51
    adiq
    -0.51
    osaurus
    -0.51
    qv
    -0.51
     Gould
    -0.50
    POSITIVE LOGITS
     regularly
    1.76
     frequently
    1.74
     every
    1.69
     periodically
    1.59
     occasionally
    1.53
     daily
    1.51
     constantly
    1.51
     often
    1.51
    every
    1.50
     weekly
    1.50
    Activations Density 7.669%

    No Known Activations