© 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. 28836
    Prev
    Next
    INDEX
    Explanations

    phrases that reference legal or scientific violations against established norms

    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
    69
    +0.11
    0.5%
    654
    +0.10
    0.4%
    275
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.03
    314
    +0.10
    -0.00
    232
    +0.09
    0.03
    Negative Logits
    iq
    -0.90
     partName
    -0.73
    NetMessage
    -0.72
    ical
    -0.71
    omach
    -0.67
    */(
    -0.67
    ics
    -0.66
    ICS
    -0.65
    icans
    -0.64
     precincts
    -0.62
    POSITIVE LOGITS
    ventions
    1.05
    vention
    0.92
    ptions
    0.92
    ven
    0.91
     Lanka
    0.87
    ption
    0.83
    vern
    0.83
    AGE
    0.79
     Lank
    0.78
    ppy
    0.76
    Activations Density 0.171%

    No Known Activations