© 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 EvalsExportsinterp-engineNEWAPI 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. 32276
    Prev
    Next
    INDEX
    Explanations

    terms related to morality and moral character

    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
    287
    +0.14
    0.6%
    118
    +0.12
    0.5%
    25
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.02
    103
    +0.12
    0.01
    187
    +0.11
    0.01
    Negative Logits
    glers
    -0.74
    ĭ
    -0.69
    MT
    -0.66
    lings
    -0.65
    tes
    -0.62
    ãĥĥãĥĪ
    -0.62
     Fargo
    -0.61
    ty
    -0.58
    =]
    -0.58
    GV
    -0.57
    POSITIVE LOGITS
    negie
    0.91
    aterial
    0.90
    antle
    0.90
    ovable
    0.87
    cul
    0.86
    pi
    0.85
    conservancy
    0.81
    or
    0.79
    illian
    0.78
    pora
    0.77
    Activations Density 0.043%

    No Known Activations