© 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. 27439
    Prev
    Next
    INDEX
    Explanations

    numeric values, particularly focusing on various ranges and significance

    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
    281
    +0.11
    0.5%
    718
    +0.11
    0.5%
    695
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.11
    0.06
    326
    +0.11
    0.06
    316
    +0.10
    0.05
    Negative Logits
    uve
    -0.76
    soDeliveryDate
    -0.72
    ression
    -0.70
    ngth
    -0.70
    enery
    -0.68
    ways
    -0.67
    orship
    -0.64
    ressive
    -0.64
    undai
    -0.62
    chnology
    -0.62
    POSITIVE LOGITS
    318
    1.14
    317
    1.07
    322
    1.06
    326
    1.05
    311
    1.04
    316
    1.04
    440
    1.03
    327
    1.03
    328
    1.02
    312
    1.02
    Activations Density 0.578%

    No Known Activations