© 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. 27830
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "any"

    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
    750
    +0.11
    0.5%
    374
    +0.10
    0.5%
    497
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.11
    0.03
    216
    +0.10
    0.03
    402
    +0.10
    0.03
    Negative Logits
    ugu
    -0.79
    IDES
    -0.69
    ulner
    -0.69
    ãĤ©
    -0.67
    ãĤ¡
    -0.66
    redients
    -0.66
    umenthal
    -0.65
    cffff
    -0.64
    osterone
    -0.64
    verbs
    -0.64
    POSITIVE LOGITS
     case
    1.12
     respect
    0.97
     circumstance
    0.95
     respects
    0.94
     CASE
    0.91
     capacity
    0.88
     regard
    0.86
     direction
    0.85
     meaningful
    0.83
     event
    0.81
    Activations Density 0.147%

    No Known Activations