© 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. 30587
    Prev
    Next
    INDEX
    Explanations

    financial data and trends related to energy production

    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
    464
    +0.12
    0.5%
    741
    +0.11
    0.5%
    243
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.12
    0.03
    375
    +0.11
    0.05
    393
    +0.09
    0.19
    Negative Logits
    ez
    -0.75
    ophon
    -0.69
    eger
    -0.63
    clerosis
    -0.63
    hran
    -0.62
    eln
    -0.62
    ibaba
    -0.62
    ranged
    -0.61
    giene
    -0.61
    ãĥĬ
    -0.61
    POSITIVE LOGITS
     C
    2.29
    C
    1.73
     c
    1.56
    Cs
    1.15
    c
    1.14
     CIS
    1.11
     Ce
    1.09
     CAT
    1.01
     CAM
    1.00
     CM
    0.98
    Activations Density 7.576%

    No Known Activations