© 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. 8-RES_POST_32K-OAI
    11. 5478
    Prev
    Next
    INDEX
    Explanations

    topics related to environmental issues and animal rights

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    546
    +0.09
    0.4%
    304
    +0.09
    0.4%
    600
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.21
    67
    +0.09
    0.11
    57
    +0.09
    0.04
    Negative Logits
     uniforms
    -0.68
     administered
    -0.68
     Joker
    -0.65
     leased
    -0.64
    ahime
    -0.63
     takeoff
    -0.63
     defer
    -0.62
     Tests
    -0.61
     Completed
    -0.61
    lycer
    -0.61
    POSITIVE LOGITS
     advocates
    1.50
     proponents
    1.48
     skeptics
    1.44
     enthusiasts
    1.44
     detractors
    1.35
     critics
    1.31
    icion
    1.28
     enthusiast
    1.25
    Critics
    1.25
     theorists
    1.23
    Activations Density 6.878%

    No Known Activations