© 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. 30126
    Prev
    Next
    INDEX
    Explanations

    incidents related to arrests and criminal charges

    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
    631
    +0.12
    0.5%
    650
    +0.11
    0.5%
    282
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.16
    507
    +0.11
    0.11
    369
    +0.11
    0.05
    Negative Logits
     Hilton
    -0.89
     dopamine
    -0.88
    pora
    -0.85
    Mill
    -0.84
     Millennials
    -0.83
     IPO
    -0.82
     eviction
    -0.82
    annel
    -0.82
     resettlement
    -0.80
     gastro
    -0.78
    POSITIVE LOGITS
     swords
    2.19
     sword
    2.05
    Sword
    1.88
    sword
    1.87
     Swords
    1.83
     Sword
    1.77
     weapons
    1.68
    Weapon
    1.68
     weapon
    1.68
    weapon
    1.64
    Activations Density 3.729%

    No Known Activations