© 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. 10-RES_POST_32K-OAI
    11. 29461
    Prev
    Next
    INDEX
    Explanations

    concepts related to risk and risk management

    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
    488
    +0.13
    0.6%
    314
    +0.13
    0.6%
    285
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.13
    0.02
    247
    +0.13
    0.03
    439
    +0.11
    0.02
    Negative Logits
    issance
    -0.80
     Franç
    -0.66
    poons
    -0.65
     throats
    -0.65
    atters
    -0.64
    glers
    -0.63
    heses
    -0.62
    Dispatch
    -0.61
    vez
    -0.61
    eve
    -0.59
    POSITIVE LOGITS
    iest
    1.05
     aversion
    1.04
    taking
    1.00
    ier
    0.95
    iness
    0.95
     posed
    0.86
     factors
    0.83
    taker
    0.81
     assessment
    0.79
     incurred
    0.79
    Activations Density 0.151%

    No Known Activations