© 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. 27933
    Prev
    Next
    INDEX
    Explanations

    procedural instructions in a step-by-step format

    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
    326
    +0.16
    0.7%
    364
    +0.12
    0.5%
    450
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    584
    +0.16
    0.14
    352
    +0.12
    0.13
    426
    +0.11
    0.10
    Negative Logits
     outwe
    -0.69
    entious
    -0.67
     metaph
    -0.64
     deterrence
    -0.64
     theoret
    -0.64
     hosp
    -0.63
     credible
    -0.63
     Citiz
    -0.63
     causal
    -0.62
     waged
    -0.62
    POSITIVE LOGITS
     Create
    1.16
    Once
    1.13
     Prepare
    1.13
    Now
    1.12
     Once
    1.11
    Create
    1.11
     Remove
    1.09
     Now
    1.09
     Setup
    1.06
    Step
    1.06
    Activations Density 1.167%

    No Known Activations