© 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. 10-RES_POST_32K-OAI
    11. 30651
    Prev
    Next
    INDEX
    Explanations

    references to death, particularly in contexts involving violence or accidents

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

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.12
    0.6%
    759
    +0.11
    0.5%
    47
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.02
    47
    +0.11
    0.02
    85
    +0.10
    0.01
    Negative Logits
    erous
    -0.94
    yi
    -0.80
    unda
    -0.75
    orthy
    -0.69
     Dwell
    -0.68
    yang
    -0.67
     Username
    -0.67
    adra
    -0.66
    amaru
    -0.65
    nai
    -0.64
    POSITIVE LOGITS
     flaw
    0.97
     sins
    0.90
     injection
    0.88
     consequences
    0.84
     overdoses
    0.84
     flaws
    0.84
     wounds
    0.82
     combination
    0.80
     dose
    0.80
     Sins
    0.79
    Activations Density 0.102%

    No Known Activations