© 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. 30794
    Prev
    Next
    INDEX
    Explanations

    geographic locations specifically related to San Jose and its vicinity

    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
    412
    +0.14
    0.6%
    689
    +0.13
    0.6%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.05
    211
    +0.13
    0.03
    659
    +0.09
    0.04
    Negative Logits
    anism
    -0.79
     captcha
    -0.74
    DragonMagazine
    -0.72
    xual
    -0.71
    yss
    -0.71
    nown
    -0.70
    urious
    -0.68
    ursed
    -0.68
    ãģł
    -0.65
    odynamics
    -0.64
    POSITIVE LOGITS
     Plain
    0.82
     Mesa
    0.78
     Ban
    0.76
     Ced
    0.76
     Jal
    0.76
     Alto
    0.76
     Pal
    0.76
     Monte
    0.75
     Ari
    0.74
     Os
    0.73
    Activations Density 0.282%

    No Known Activations