© 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. 28697
    Prev
    Next
    INDEX
    Explanations

    mentions of members of the Trump family

    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
    29
    +0.13
    0.6%
    214
    +0.10
    0.5%
    421
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    254
    +0.13
    0.03
    696
    +0.10
    0.04
    621
    +0.09
    0.03
    Negative Logits
    ient
    -0.75
    arist
    -0.73
    er
    -0.72
    evil
    -0.71
    opus
    -0.70
    iac
    -0.66
    arium
    -0.66
    holes
    -0.66
    âķIJ
    -0.64
    Tube
    -0.64
    POSITIVE LOGITS
     Reagan
    0.89
    son
    0.87
    kson
    0.85
     Trump
    0.84
    trump
    0.67
    Trump
    0.64
     Ivanka
    0.62
    SE
    0.62
     Chapman
    0.62
     Goose
    0.60
    Activations Density 0.325%

    No Known Activations