© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 26501
    Prev
    Next
    INDEX
    Explanations

    phrases related to knowledge or awareness

    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
    689
    +0.10
    0.5%
    407
    +0.10
    0.5%
    140
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.10
    0.15
    139
    +0.10
    0.14
    718
    +0.10
    0.14
    Negative Logits
     smashing
    -0.74
    luster
    -0.73
     moderation
    -0.67
     Reneg
    -0.66
    emale
    -0.66
     scra
    -0.66
     menstrual
    -0.65
     festive
    -0.64
    mercial
    -0.64
     rejuven
    -0.63
    POSITIVE LOGITS
     know
    1.54
     knows
    1.52
    know
    1.50
    Know
    1.50
     knew
    1.49
     KNOW
    1.48
     Know
    1.46
    Knowing
    1.33
     knowing
    1.31
    knowledge
    1.27
    Activations Density 2.716%

    No Known Activations