© 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. 29131
    Prev
    Next
    INDEX
    Explanations

    actions involving physical contact or movement

    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
    373
    +0.15
    0.7%
    654
    +0.11
    0.5%
    165
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    654
    +0.15
    0.05
    569
    +0.11
    0.05
    123
    +0.11
    0.05
    Negative Logits
     redes
    -0.77
     psychiat
    -0.70
     mathemat
    -0.68
    iculture
    -0.67
    Introduced
    -0.66
     submar
    -0.65
    artifacts
    -0.64
     professions
    -0.64
     enthusi
    -0.63
    vernment
    -0.63
    POSITIVE LOGITS
     hers
    0.98
     mine
    0.95
     ours
    0.88
     his
    0.85
     Viktor
    0.85
     Zoe
    0.84
     Weiss
    0.83
     my
    0.83
     Toby
    0.81
     Luke
    0.81
    Activations Density 0.453%

    No Known Activations