© 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. 28767
    Prev
    Next
    INDEX
    Explanations

    references to political figures and parties

    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
    21
    +0.15
    0.7%
    373
    +0.15
    0.7%
    155
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.10
    103
    +0.15
    0.05
    314
    +0.10
    0.01
    Negative Logits
     CONTIN
    -0.73
    advertising
    -0.70
    ////////
    -0.67
    furt
    -0.65
    ÙĨ
    -0.62
    fb
    -0.62
    Secondly
    -0.62
     CrossRef
    -0.61
     Mongol
    -0.61
    kHz
    -0.61
    POSITIVE LOGITS
    atin
    0.76
    agy
    0.70
    angan
    0.70
    alsh
    0.68
    ota
    0.68
    arge
    0.68
    heny
    0.67
    athy
    0.66
    aith
    0.65
    atch
    0.63
    Activations Density 0.429%

    No Known Activations