© 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. 28252
    Prev
    Next
    INDEX
    Explanations

    instances of the word "focus" and related variations in context

    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
    549
    +0.11
    0.5%
    624
    +0.10
    0.5%
    726
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    296
    +0.11
    0.03
    665
    +0.10
    0.03
    595
    +0.10
    0.03
    Negative Logits
    mia
    -0.93
    ania
    -0.71
    corn
    -0.68
    DragonMagazine
    -0.65
    ozo
    -0.65
    Afee
    -0.64
    mx
    -0.63
     externalToEVAOnly
    -0.62
    igans
    -0.62
    AFTA
    -0.62
    POSITIVE LOGITS
    rite
    0.96
     groups
    0.86
     group
    0.82
     Groups
    0.77
    rals
    0.73
     shifts
    0.72
     Areas
    0.72
     Group
    0.70
     areas
    0.69
    ively
    0.68
    Activations Density 0.135%

    No Known Activations