© 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. 28307
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers in programming or data structures

    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
    314
    +0.15
    0.7%
    627
    +0.11
    0.5%
    560
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.15
    0.00
    232
    +0.11
    0.04
    588
    +0.11
    0.03
    Negative Logits
     GEAR
    -0.83
     hats
    -0.75
     interchange
    -0.73
     helmets
    -0.73
    theless
    -0.73
     nem
    -0.71
     briefs
    -0.70
     TECH
    -0.70
     DRAG
    -0.69
     lows
    -0.69
    POSITIVE LOGITS
    perties
    1.08
    ventory
    1.07
    Dial
    1.03
    Context
    1.00
    atable
    1.00
    utor
    0.99
    ository
    0.98
    roller
    0.96
    Button
    0.96
    Property
    0.96
    Activations Density 0.289%

    No Known Activations