© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6393
    Prev
    Next
    INDEX
    Explanations

    themes related to gun violence and hate crimes

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    516
    +0.12
    0.5%
    346
    +0.11
    0.5%
    125
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    516
    +0.12
    0.09
    199
    +0.11
    0.12
    85
    +0.10
    0.09
    Negative Logits
    dit
    -0.80
     Accounting
    -0.76
    DIR
    -0.76
     TTL
    -0.75
    pod
    -0.74
     Patent
    -0.73
     royalties
    -0.73
     curing
    -0.71
     Dry
    -0.70
    DOC
    -0.69
    POSITIVE LOGITS
     violence
    1.20
     gunman
    1.16
    ottesville
    1.15
     terrorist
    1.11
     shootings
    1.09
     extremist
    1.08
    Muslim
    1.04
     extremists
    1.03
     rampage
    1.03
     assailant
    1.02
    Activations Density 5.332%

    No Known Activations