© 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. 32047
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" as well as contexts indicating inclusion or involvement

    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
    373
    +0.12
    0.6%
    475
    +0.09
    0.4%
    357
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.12
    0.06
    22
    +0.09
    0.04
    393
    +0.09
    0.07
    Negative Logits
    lees
    -0.98
    indal
    -0.88
    FTWARE
    -0.83
    mber
    -0.83
    krit
    -0.81
    ptives
    -0.80
    DragonMagazine
    -0.80
    20439
    -0.79
    skirts
    -0.79
    bench
    -0.76
    POSITIVE LOGITS
     impro
    0.75
     unusually
    0.72
     incidentally
    0.72
     paraph
    0.71
     plaus
    0.70
     surprisingly
    0.69
     coinc
    0.69
     unexpectedly
    0.66
     guessed
    0.66
     unbelievably
    0.65
    Activations Density 1.017%

    No Known Activations