© 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. 26673
    Prev
    Next
    INDEX
    Explanations

    instances of specific named entities or groups

    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
    464
    +0.15
    0.7%
    373
    +0.14
    0.7%
    506
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.15
    -0.06
    314
    +0.14
    -0.02
    659
    +0.11
    0.04
    Negative Logits
    MpServer
    -0.79
    ourt
    -0.73
    schild
    -0.71
    tes
    -0.69
    ls
    -0.68
    bats
    -0.67
     Kessler
    -0.66
    papers
    -0.65
    te
    -0.65
    haar
    -0.64
    POSITIVE LOGITS
    emed
    0.65
    onal
    0.65
     miss
    0.65
    istically
    0.63
    iculture
    0.56
    EM
    0.55
    aned
    0.53
    ese
    0.53
    icum
    0.53
    ana
    0.52
    Activations Density 0.981%

    No Known Activations