© 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. 27732
    Prev
    Next
    INDEX
    Explanations

    references to safety and well-being in community contexts

    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
    102
    +0.12
    0.5%
    370
    +0.09
    0.4%
    556
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.12
    0.16
    566
    +0.09
    0.12
    55
    +0.09
    0.13
    Negative Logits
     Puzz
    -0.74
     puzz
    -0.72
     ado
    -0.71
     limbo
    -0.70
     fallacy
    -0.69
     Explosion
    -0.69
     Decay
    -0.69
    ibble
    -0.69
     Farn
    -0.68
     blasphemy
    -0.68
    POSITIVE LOGITS
     able
    1.35
     competent
    1.17
     adequately
    1.13
     prepared
    1.13
     ready
    1.12
     safe
    1.12
     comfortable
    1.12
     capable
    1.11
     knowledgeable
    1.05
     trustworthy
    1.04
    Activations Density 0.923%

    No Known Activations