© 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. 29793
    Prev
    Next
    INDEX
    Explanations

    numerical data related to financial metrics

    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
    409
    +0.12
    0.5%
    417
    +0.10
    0.4%
    711
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.12
    0.08
    6
    +0.10
    0.08
    107
    +0.10
    0.07
    Negative Logits
    apult
    -0.74
    ritten
    -0.73
    onyms
    -0.70
    agall
    -0.69
    ĨĴ
    -0.68
    ĸļ
    -0.67
    geon
    -0.65
     readable
    -0.63
    hens
    -0.62
    sized
    -0.62
    POSITIVE LOGITS
     goodwill
    0.71
     Profit
    0.66
     Investments
    0.65
     SUP
    0.63
     Unreal
    0.61
     Pep
    0.57
     Jonas
    0.57
    heimer
    0.57
    Property
    0.57
    Trend
    0.57
    Activations Density 0.458%

    No Known Activations