© 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. 30430
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and expressions, particularly within the context of notation and evaluation

    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
    184
    +0.11
    0.5%
    226
    +0.11
    0.5%
    292
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.11
    0.13
    326
    +0.11
    0.12
    435
    +0.11
    0.08
    Negative Logits
    Ĥª
    -0.99
     HG
    -0.86
    avorite
    -0.82
    Torrent
    -0.80
    Ore
    -0.78
     Yor
    -0.78
     Cumber
    -0.77
     NAV
    -0.77
     Morty
    -0.77
    ppa
    -0.75
    POSITIVE LOGITS
    expression
    1.45
     expr
    1.33
     clause
    1.33
     clauses
    1.27
     expression
    1.24
    expr
    1.21
     expressions
    1.19
    Statement
    1.18
     conditional
    1.17
    statement
    1.16
    Activations Density 1.784%

    No Known Activations