© 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. 30276
    Prev
    Next
    INDEX
    Explanations

    monetary values or financial figures

    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
    400
    +0.10
    0.5%
    673
    +0.10
    0.5%
    689
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.10
    0.07
    430
    +0.10
    0.06
    153
    +0.10
    0.06
    Negative Logits
     ALP
    -0.67
    ardless
    -0.65
     Fn
    -0.65
     LD
    -0.63
    =>
    -0.58
    NULL
    -0.58
     KDE
    -0.58
     Duff
    -0.58
    \<
    -0.57
     shy
    -0.57
    POSITIVE LOGITS
    787
    0.77
    omo
    0.74
    rail
    0.71
    opa
    0.68
    uni
    0.68
    izer
    0.67
    olls
    0.66
    465
    0.64
    glass
    0.63
    REAM
    0.62
    Activations Density 0.286%

    No Known Activations