© 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. 28686
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and codes associated with data or identifiers

    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
    175
    +0.10
    0.5%
    725
    +0.10
    0.4%
    373
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.10
    0.04
    284
    +0.10
    0.04
    326
    +0.10
    0.06
    Negative Logits
    th
    -0.95
    teenth
    -0.89
    mith
    -0.72
    71
    -0.69
    hyde
    -0.67
    ä½ľ
    -0.64
     hypothetical
    -0.63
    73
    -0.63
    42
    -0.63
    bara
    -0.63
    POSITIVE LOGITS
    128
    0.79
    igor
    0.78
    123
    0.78
    124
    0.77
    126
    0.75
    125
    0.71
    129
    0.71
    ique
    0.71
    120
    0.70
    uct
    0.70
    Activations Density 0.584%

    No Known Activations