© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 30020
    Prev
    Next
    INDEX
    Explanations

    connections between nerve cells and their functions

    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
    418
    +0.10
    0.5%
    690
    +0.10
    0.5%
    491
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.10
    0.10
    720
    +0.10
    0.11
    546
    +0.09
    0.09
    Negative Logits
    ariat
    -0.70
     sectarian
    -0.69
     vigilante
    -0.69
     curfew
    -0.66
    chwitz
    -0.63
     unanimous
    -0.63
     unanim
    -0.63
     conscientious
    -0.63
     earnest
    -0.62
    cientious
    -0.62
    POSITIVE LOGITS
     causing
    1.02
     slowing
    0.98
     decreasing
    0.97
    forming
    0.93
     producing
    0.91
     inhib
    0.91
     forming
    0.90
     releasing
    0.88
     molecules
    0.87
     particles
    0.86
    Activations Density 0.709%

    No Known Activations