© 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 EvalsExportsAPI 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. 6203
    Prev
    Next
    INDEX
    Explanations

    instances of the word "by" in various contexts, particularly in relation to actions or submissions

    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
    116
    +0.10
    0.5%
    8
    +0.10
    0.5%
    585
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.10
    0.04
    608
    +0.10
    0.04
    192
    +0.10
    0.03
    Negative Logits
    appiness
    -0.68
    schild
    -0.68
     WATCHED
    -0.66
     rightly
    -0.63
    naires
    -0.63
     Buddy
    -0.61
    kson
    -0.60
    bes
    -0.58
    steen
    -0.58
     worries
    -0.57
    POSITIVE LOGITS
     Sponsor
    0.76
    ocket
    0.75
     proclamation
    0.70
     reason
    0.69
    Fax
    0.69
    inth
    0.67
    Tele
    0.64
     amendment
    0.64
    NetMessage
    0.63
    Registration
    0.63
    Activations Density 0.197%

    No Known Activations