© 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. 29893
    Prev
    Next
    INDEX
    Explanations

    references to various types of pie

    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
    381
    +0.11
    0.5%
    84
    +0.10
    0.5%
    111
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.04
    76
    +0.10
    0.02
    343
    +0.10
    0.02
    Negative Logits
    sers
    -0.73
    hirt
    -0.72
    suit
    -0.70
    worthiness
    -0.69
    urst
    -0.69
     Arabia
    -0.62
    spring
    -0.62
    liner
    -0.61
     Aval
    -0.61
    enough
    -0.61
    POSITIVE LOGITS
    asus
    1.01
    ople
    0.85
    ozo
    0.82
    ilon
    0.80
    achy
    0.79
    artisan
    0.79
    sylvania
    0.76
    ced
    0.75
     pie
    0.75
    eta
    0.74
    Activations Density 0.247%

    No Known Activations