© 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. 29293
    Prev
    Next
    INDEX
    Explanations

    proper nouns and entities related to people or names in various contexts

    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
    115
    +0.10
    0.4%
    9
    +0.09
    0.4%
    497
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.02
    649
    +0.09
    0.00
    424
    +0.09
    0.01
    Negative Logits
    alos
    -0.73
    gone
    -0.63
    iets
    -0.61
    nia
    -0.58
    icism
    -0.57
    isol
    -0.56
    ebus
    -0.56
    orously
    -0.56
    Ô
    -0.56
    ships
    -0.54
    POSITIVE LOGITS
    Family
    0.66
    soType
    0.65
    neau
    0.63
     dish
    0.63
    hander
    0.62
     sauces
    0.62
    Photo
    0.61
    Adds
    0.60
    ãĥīãĥ©
    0.59
     Flavoring
    0.59
    Activations Density 0.110%

    No Known Activations