© 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. 5678
    Prev
    Next
    INDEX
    Explanations

    instances of non-compliance or failure to meet obligations or responsibilities

    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
    373
    +0.13
    0.6%
    450
    +0.10
    0.5%
    545
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.13
    0.05
    204
    +0.10
    0.04
    70
    +0.10
    0.04
    Negative Logits
    rities
    -0.78
    Stars
    -0.70
     Slaughter
    -0.65
    bour
    -0.63
     ILCS
    -0.62
     Hurt
    -0.61
     Depression
    -0.60
    vantage
    -0.59
     Zerg
    -0.59
     Lur
    -0.58
    POSITIVE LOGITS
     comply
    0.86
     promptly
    0.79
    ewitness
    0.75
     diligence
    0.75
     timely
    0.70
     negligent
    0.69
     inspection
    0.68
    eret
    0.67
     diligent
    0.67
     filings
    0.67
    Activations Density 0.379%

    No Known Activations