© 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 EvalsExportsinterp-engineNEWAPI 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. 27698
    Prev
    Next
    INDEX
    Explanations

    mentions of North Korea

    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
    314
    +0.19
    0.9%
    385
    +0.11
    0.5%
    758
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.19
    0.03
    232
    +0.11
    0.04
    612
    +0.11
    0.03
    Negative Logits
    rative
    -0.63
    xxxxxxxx
    -0.63
     Moreno
    -0.60
     tee
    -0.60
    ration
    -0.59
     pinch
    -0.59
     confir
    -0.57
    natureconservancy
    -0.56
     squid
    -0.56
     declass
    -0.56
    POSITIVE LOGITS
    ampton
    1.38
    umber
    1.16
    western
    1.15
     Carolina
    1.13
    west
    1.12
    ridge
    1.09
    rup
    1.06
    woods
    1.04
    rop
    1.03
     Pole
    1.01
    Activations Density 0.205%

    No Known Activations