© 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. 29851
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to government and legal positions

    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
    224
    +0.14
    0.7%
    314
    +0.14
    0.6%
    203
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.14
    0.09
    146
    +0.14
    0.05
    371
    +0.10
    0.06
    Negative Logits
     Artist
    -0.73
    MpServer
    -0.70
    esville
    -0.68
     Artists
    -0.66
     Warfare
    -0.66
    Property
    -0.65
     loudspe
    -0.64
    Management
    -0.64
     Property
    -0.63
     Producer
    -0.63
    POSITIVE LOGITS
    ial
    0.80
     nominee
    0.80
    inelli
    0.78
     overseeing
    0.77
     resigned
    0.77
    ially
    0.76
     designate
    0.75
    alty
    0.72
    IAL
    0.71
    iate
    0.70
    Activations Density 0.543%

    No Known Activations