© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 31991
    Prev
    Next
    INDEX
    Explanations

    references to sexual misconduct and abuse

    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
    95
    +0.11
    0.5%
    433
    +0.10
    0.5%
    15
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.11
    0.07
    719
    +0.10
    0.05
    639
    +0.10
    0.04
    Negative Logits
    ItemTracker
    -0.74
    iculture
    -0.71
     psychiat
    -0.69
    successful
    -0.68
     lawy
    -0.66
    bred
    -0.66
    */(
    -0.65
    CVE
    -0.64
    adian
    -0.64
    IVERS
    -0.61
    POSITIVE LOGITS
     grop
    0.85
     mol
    0.85
     touching
    0.83
     assault
    0.83
     assaulting
    0.82
     advances
    0.81
     misconduct
    0.80
     intimate
    0.80
     battery
    0.77
     relationship
    0.75
    Activations Density 1.111%

    No Known Activations