© 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. 8-RES_POST_32K-OAI
    11. 7012
    Prev
    Next
    INDEX
    Explanations

    mentions of daughters and their familial relationships

    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
    549
    +0.12
    0.6%
    383
    +0.10
    0.5%
    394
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    318
    +0.12
    0.03
    141
    +0.10
    0.03
    383
    +0.10
    0.03
    Negative Logits
     constitu
    -0.71
    terson
    -0.67
     myster
    -0.66
     freight
    -0.61
    ãĥ¢
    -0.61
    uclear
    -0.60
    GoldMagikarp
    -0.59
    izen
    -0.59
     hazards
    -0.59
     dstg
    -0.57
    POSITIVE LOGITS
     Ivanka
    0.86
    nets
    0.84
    heses
    0.80
    daughter
    0.78
     daughters
    0.78
    hetically
    0.76
    ILY
    0.75
     born
    0.74
    riages
    0.73
     Daughter
    0.73
    Activations Density 0.080%

    No Known Activations