© 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. 8-RES_POST_32K-OAI
    6. 6053
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of outerwear, specifically coats and jackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    314
    +0.14
    0.6%
    285
    +0.10
    0.4%
    652
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    652
    +0.14
    0.02
    326
    +0.10
    0.01
    78
    +0.10
    0.01
    Negative Logits
    nir
    -0.66
    iates
    -0.63
     Kut
    -0.62
    perse
    -0.62
     Sabha
    -0.61
    chuk
    -0.60
    KNOWN
    -0.59
     Controlled
    -0.58
    Pad
    -0.58
     Zar
    -0.58
    POSITIVE LOGITS
     tails
    0.84
    pins
    0.82
    ings
    0.81
     Coat
    0.77
     coat
    0.74
    manship
    0.71
    grain
    0.69
    meal
    0.69
    wit
    0.68
    folios
    0.68
    Activations Density 0.041%

    No Known Activations