© 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. 9102
    Prev
    Next
    INDEX
    Explanations

    terms related to political or societal upheaval and legal actions

    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
    373
    +0.23
    1.1%
    31
    +0.10
    0.5%
    651
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.23
    0.10
    503
    +0.10
    0.06
    314
    +0.10
    0.01
    Negative Logits
     cannabin
    -0.79
     learners
    -0.73
     empath
    -0.72
     imperfect
    -0.72
     verbs
    -0.71
     logically
    -0.71
     acron
    -0.71
     intuitive
    -0.71
     descript
    -0.70
     antioxid
    -0.69
    POSITIVE LOGITS
    illation
    1.13
    ification
    1.11
    ruption
    1.10
    ction
    1.05
    iversary
    1.03
    isation
    1.02
    urrence
    1.01
    osure
    1.01
    ctions
    1.00
    rection
    1.00
    Activations Density 1.114%

    No Known Activations