© 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. 31114
    Prev
    Next
    INDEX
    Explanations

    terminology related to defense spending and military affairs

    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
    234
    +0.12
    0.6%
    573
    +0.10
    0.4%
    52
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    482
    +0.12
    0.01
    314
    +0.10
    -0.01
    374
    +0.09
    -0.01
    Negative Logits
    idden
    -0.76
    ainted
    -0.75
    uez
    -0.72
     viz
    -0.71
    âĹ¼
    -0.70
     autonom
    -0.66
     [+
    -0.65
    olean
    -0.65
     conce
    -0.65
    :[
    -0.64
    POSITIVE LOGITS
    .>>
    1.33
     }}
    1.13
     Deadline
    0.99
     Recomm
    0.96
     prec
    0.85
    }}
    0.81
     Certification
    0.77
     note
    0.76
    >>
    0.75
     Applic
    0.73
    Activations Density 0.120%

    No Known Activations