© 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. 29593
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions, particularly instances of "and."

    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
    423
    +0.11
    0.5%
    764
    +0.11
    0.5%
    126
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.11
    0.05
    393
    +0.11
    0.08
    96
    +0.09
    0.05
    Negative Logits
    ermanent
    -0.66
     Accuracy
    -0.65
    èĢħ
    -0.65
     Absolute
    -0.64
     Effective
    -0.63
     Agents
    -0.62
    Helper
    -0.61
    oulos
    -0.61
     mitigation
    -0.61
    Asset
    -0.61
    POSITIVE LOGITS
     fro
    1.03
     fuss
    0.84
     fart
    0.84
     gamb
    0.82
     tremb
    0.82
     jugg
    0.82
     weep
    0.81
     whist
    0.80
     gro
    0.80
     gib
    0.80
    Activations Density 1.188%

    No Known Activations