© 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. 31744
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that introduce clarifications or specifications

    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
    551
    +0.17
    0.8%
    282
    +0.17
    0.8%
    49
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.17
    0.07
    109
    +0.17
    0.06
    551
    +0.16
    0.06
    Negative Logits
     doesnt
    -1.01
     recognizes
    -1.00
     feels
    -0.99
     sleeps
    -0.98
     sees
    -0.97
     remembers
    -0.96
     thinks
    -0.96
     believes
    -0.96
     succeeds
    -0.96
     awaits
    -0.95
    POSITIVE LOGITS
     are
    1.19
     aren
    1.13
     constitute
    1.09
     ARE
    1.06
     vary
    1.04
     comprise
    1.04
     differ
    1.03
     were
    1.02
     abound
    1.01
     have
    1.00
    Activations Density 0.147%

    No Known Activations