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

    Neuronpedia

    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. 4593
    Prev
    Next
    INDEX
    Explanations

    phrases regarding the use of force or violence

    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
    329
    +0.12
    0.6%
    60
    +0.12
    0.5%
    509
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.12
    0.03
    705
    +0.12
    0.03
    520
    +0.10
    0.03
    Negative Logits
    llor
    -0.68
    ï¸ı
    -0.68
    nings
    -0.66
    cellence
    -0.66
    etsk
    -0.62
    hower
    -0.62
    ablishment
    -0.60
    YY
    -0.60
    iae
    -0.60
    owship
    -0.59
    POSITIVE LOGITS
     sparing
    0.92
     antibiotics
    0.87
     tools
    0.86
     condoms
    0.86
     discretion
    0.85
     aliases
    0.85
     force
    0.84
     contraceptives
    0.84
     pesticides
    0.80
     coercion
    0.80
    Activations Density 0.109%

    No Known Activations