© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29834
    Prev
    Next
    INDEX
    Explanations

    conjunctions indicating relationships and conditions in sentences

    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
    410
    +0.11
    0.5%
    628
    +0.09
    0.4%
    574
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.11
    0.04
    393
    +0.09
    0.05
    631
    +0.09
    0.03
    Negative Logits
    nob
    -0.61
    ois
    -0.61
     Taxes
    -0.61
     Wonders
    -0.59
     Tycoon
    -0.59
     Safari
    -0.58
    ouse
    -0.58
     Tackle
    -0.57
     queens
    -0.57
     Trog
    -0.57
    POSITIVE LOGITS
     imagined
    0.93
     simulated
    0.89
     perceived
    0.86
     inferred
    0.82
     suspected
    0.82
     prospective
    0.81
     implied
    0.81
     projected
    0.80
     foreseeable
    0.77
    ifice
    0.77
    Activations Density 0.441%

    No Known Activations