© 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. 30442
    Prev
    Next
    INDEX
    Explanations

    references to individuals' names, particularly those of notable people

    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
    157
    +0.12
    0.5%
    582
    +0.12
    0.5%
    759
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.03
    288
    +0.12
    0.04
    314
    +0.11
    -0.01
    Negative Logits
    icity
    -1.04
    oline
    -0.93
    esm
    -0.91
    ial
    -0.87
    iour
    -0.83
    daq
    -0.82
    icans
    -0.80
    ively
    -0.78
    ic
    -0.78
    ician
    -0.78
    POSITIVE LOGITS
    Ĺ
    0.84
    roy
    0.74
     Dread
    0.69
    FORE
    0.67
    wise
    0.66
    backer
    0.65
    ilipp
    0.64
    awei
    0.63
     Arcade
    0.63
    EAR
    0.63
    Activations Density 0.354%

    No Known Activations