© 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. 32675
    Prev
    Next
    INDEX
    Explanations

    the word "jalapeño."

    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
    429
    +0.12
    0.5%
    103
    +0.11
    0.5%
    284
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.06
    284
    +0.11
    0.04
    314
    +0.10
    -0.00
    Negative Logits
     receptions
    -0.64
     horizont
    -0.63
    £ı
    -0.63
    ĸļ
    -0.63
    matter
    -0.62
    finding
    -0.60
     showers
    -0.59
     DG
    -0.59
     floors
    -0.59
     principals
    -0.59
    POSITIVE LOGITS
    eno
    1.06
    arte
    1.02
    enos
    0.89
    aug
    0.86
    utan
    0.84
    ahime
    0.84
    ova
    0.82
    utor
    0.82
    aceae
    0.81
    aho
    0.80
    Activations Density 0.364%

    No Known Activations