© 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. 30065
    Prev
    Next
    INDEX
    Explanations

    numerical values representing populations or counts

    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
    373
    +0.13
    0.6%
    663
    +0.10
    0.5%
    230
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.13
    0.06
    238
    +0.10
    0.05
    223
    +0.09
    0.06
    Negative Logits
    cho
    -0.72
    ggles
    -0.70
     lifes
    -0.64
    catching
    -0.63
    hest
    -0.62
     paran
    -0.62
     Pros
    -0.62
    tp
    -0.61
    liest
    -0.61
    NetMessage
    -0.61
    POSITIVE LOGITS
    123
    0.87
    128
    0.81
    125
    0.81
    129
    0.77
    198
    0.76
    194
    0.74
     trillion
    0.73
    120
    0.72
    ¿½
    0.71
    127
    0.70
    Activations Density 0.666%

    No Known Activations