© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 26709
    Prev
    Next
    INDEX
    Explanations

    instances of the indefinite article "a" followed by adjectives or descriptive phrases

    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
    476
    +0.10
    0.5%
    404
    +0.10
    0.4%
    655
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.10
    36
    +0.10
    0.10
    159
    +0.09
    0.06
    Negative Logits
    lio
    -0.87
    sburg
    -0.72
    igne
    -0.71
    anwhile
    -0.66
    raf
    -0.65
    deen
    -0.64
    :{
    -0.64
     Rebell
    -0.63
     withd
    -0.63
    here
    -0.63
    POSITIVE LOGITS
     vengeance
    1.25
     bang
    1.19
     emphasis
    1.10
     regard
    1.07
     twist
    1.06
     impunity
    1.06
     flourish
    1.05
     caveat
    1.03
     regards
    1.02
     hindsight
    0.99
    Activations Density 1.043%

    No Known Activations