© 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. 26212
    Prev
    Next
    INDEX
    Explanations

    instances of detailed descriptions or accounts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    302
    +0.13
    0.6%
    455
    +0.10
    0.5%
    561
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.13
    0.01
    455
    +0.10
    0.03
    47
    +0.10
    0.02
    Negative Logits
    soDeliveryDate
    -0.79
     Nicaragua
    -0.77
    oi
    -0.76
    enos
    -0.75
    aden
    -0.73
    oster
    -0.71
    atan
    -0.69
    encrypted
    -0.69
    aspers
    -0.69
    awa
    -0.68
    POSITIVE LOGITS
     instructions
    0.95
     descriptions
    0.92
     description
    0.90
    lly
    0.82
    bred
    0.82
     knowledge
    0.79
     explanation
    0.79
     explanations
    0.78
    ness
    0.77
     detail
    0.77
    Activations Density 0.104%

    No Known Activations