© 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. 10-RES_POST_32K-OAI
    11. 28663
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "DA" or similar patterns often related to organizational names or acronyms

    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
    456
    +0.12
    0.6%
    630
    +0.11
    0.5%
    339
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    -0.01
    406
    +0.11
    0.03
    634
    +0.11
    0.03
    Negative Logits
    ties
    -0.74
    igator
    -0.73
    ments
    -0.72
    dogs
    -0.71
    ements
    -0.69
    ocal
    -0.69
    anamo
    -0.67
     WATCHED
    -0.67
    cies
    -0.66
    igation
    -0.65
    POSITIVE LOGITS
    ILY
    1.39
    VID
    1.17
    hyde
    0.97
    uster
    0.76
    usters
    0.72
    ESH
    0.71
    roid
    0.71
    VIS
    0.70
    VICE
    0.69
    ÄŁ
    0.69
    Activations Density 0.360%

    No Known Activations