© 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. 30335
    Prev
    Next
    INDEX
    Explanations

    contexts related to health crises and emergency situations

    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
    218
    +0.13
    0.6%
    116
    +0.12
    0.5%
    209
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.13
    0.08
    469
    +0.12
    0.07
    323
    +0.10
    0.05
    Negative Logits
    20439
    -0.75
     precedent
    -0.67
    âĦ¢:
    -0.67
    yrights
    -0.66
    cript
    -0.64
    adays
    -0.63
     pronunciation
    -0.59
     343
    -0.58
     locality
    -0.58
    onomy
    -0.58
    POSITIVE LOGITS
     agony
    1.23
     pain
    1.04
     distress
    1.03
     anguish
    0.95
     danger
    0.95
     shock
    0.95
     peril
    0.94
     trouble
    0.92
     excruciating
    0.90
     tears
    0.87
    Activations Density 0.587%

    No Known Activations