© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 27023
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistics

    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
    +0.23
    1.1%
    188
    +0.11
    0.5%
    509
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.23
    0.12
    153
    +0.11
    0.11
    488
    +0.10
    0.09
    Negative Logits
    oyer
    -0.68
    ilic
    -0.66
     Emin
    -0.66
    amphetamine
    -0.63
    SpaceEngineers
    -0.61
    Store
    -0.60
    Tokens
    -0.60
    Ħ¢
    -0.60
    mast
    -0.60
     EntityItem
    -0.59
    POSITIVE LOGITS
    instead
    0.69
     proportion
    0.66
    ign
    0.66
     percentage
    0.63
    among
    0.63
    ivil
    0.62
    against
    0.61
     thirds
    0.59
     poles
    0.58
    uge
    0.58
    Activations Density 0.572%

    No Known Activations