© 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. 26300
    Prev
    Next
    INDEX
    Explanations

    elements related to suspicion and inquiries into accountability

    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
    586
    +0.14
    0.6%
    115
    +0.11
    0.5%
    544
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.14
    0.12
    566
    +0.11
    0.11
    496
    +0.10
    0.13
    Negative Logits
     Became
    -0.63
    ģĸ
    -0.59
     Cruel
    -0.58
    UTF
    -0.56
    uras
    -0.55
    \":
    -0.53
    mentioned
    -0.53
    eness
    -0.53
     acron
    -0.52
    SI
    -0.50
    POSITIVE LOGITS
     instead
    1.74
     merely
    1.67
    Instead
    1.62
     Instead
    1.52
     simply
    1.39
    Rather
    1.33
     Rather
    1.27
    instead
    1.25
     rather
    1.21
     just
    1.11
    Activations Density 2.418%

    No Known Activations