© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29883
    Prev
    Next
    INDEX
    Explanations

    phrases concerning the significance or implications of concepts

    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
    383
    +0.15
    0.7%
    497
    +0.11
    0.5%
    679
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    759
    +0.15
    0.05
    271
    +0.11
    0.04
    531
    +0.10
    0.04
    Negative Logits
     Thames
    -0.62
     tamp
    -0.59
     Santana
    -0.58
    mson
    -0.57
    tan
    -0.56
    Americ
    -0.56
     indecent
    -0.56
    cknow
    -0.56
    robat
    -0.56
    conn
    -0.56
    POSITIVE LOGITS
    inks
    0.73
     exactly
    0.72
    IX
    0.71
     clinically
    0.70
    Exactly
    0.70
    abouts
    0.70
    entially
    0.70
    cript
    0.69
    ife
    0.67
     aest
    0.65
    Activations Density 0.380%

    No Known Activations