© 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. 8-RES_POST_32K-OAI
    11. 5990
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "John"

    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
    430
    +0.10
    0.5%
    504
    +0.10
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.05
    659
    +0.10
    0.04
    141
    +0.10
    0.04
    Negative Logits
    ktop
    -0.90
    tar
    -0.81
    ategory
    -0.81
    razen
    -0.74
    hower
    -0.72
    pora
    -0.71
    otide
    -0.71
    terday
    -0.71
    BALL
    -0.70
    chnology
    -0.69
    POSITIVE LOGITS
     Piper
    0.91
    sworth
    0.79
     Winchester
    0.73
    wise
    0.73
     Percy
    0.72
     Chrys
    0.71
     Hopkins
    0.68
    itably
    0.67
     Evans
    0.67
     McGregor
    0.65
    Activations Density 0.166%

    No Known Activations