© 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. 28156
    Prev
    Next
    INDEX
    Explanations

    geographical locations and their relevance to events

    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
    373
    +0.12
    0.5%
    383
    +0.10
    0.4%
    694
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.10
    547
    +0.10
    0.06
    693
    +0.10
    0.08
    Negative Logits
    ":"/
    -0.72
     bandwagon
    -0.65
     Airl
    -0.62
    ModLoader
    -0.62
     conferences
    -0.61
     toget
    -0.61
     Cena
    -0.58
     Scholarship
    -0.57
     prevail
    -0.57
     Grail
    -0.57
    POSITIVE LOGITS
     township
    0.79
     overlooking
    0.78
    ruary
    0.76
    bright
    0.75
     Township
    0.74
     suburb
    0.73
    thur
    0.70
     northwest
    0.70
     bordering
    0.69
     northeast
    0.69
    Activations Density 0.742%

    No Known Activations