© 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. 30358
    Prev
    Next
    INDEX
    Explanations

    numerical codes and references within a dataset

    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
    53
    +0.12
    0.5%
    435
    +0.10
    0.5%
    503
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.04
    96
    +0.10
    0.04
    284
    +0.10
    0.03
    Negative Logits
    bats
    -1.04
    steen
    -0.88
    iasis
    -0.84
    aneers
    -0.82
    tower
    -0.82
    choes
    -0.79
    crit
    -0.78
    dogs
    -0.76
    shots
    -0.75
    tor
    -0.74
    POSITIVE LOGITS
    ðĿ
    0.86
     Eucl
    0.73
    ¥ŀ
    0.72
     intersect
    0.72
     âĢº
    0.70
     Å
    0.68
    ß
    0.67
    Ĵ
    0.67
     directions
    0.67
    ENTION
    0.65
    Activations Density 0.122%

    No Known Activations