© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26563
    Prev
    Next
    INDEX
    Explanations

    references to flags and anthems

    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
    288
    +0.16
    0.7%
    373
    +0.10
    0.5%
    129
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.03
    524
    +0.10
    0.02
    652
    +0.10
    0.01
    Negative Logits
     Argon
    -0.74
     Flavoring
    -0.72
    ynthesis
    -0.69
    è£ħ
    -0.67
    nesota
    -0.67
     subsequ
    -0.66
    女
    -0.66
    venants
    -0.65
     Kut
    -0.64
     defic
    -0.61
    POSITIVE LOGITS
    rant
    1.50
    pole
    1.47
    ging
    1.41
    staff
    1.29
     bearer
    1.08
    ged
    1.03
    stones
    1.01
    rants
    0.95
    gers
    0.90
    rier
    0.89
    Activations Density 0.124%

    No Known Activations