© 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. 6031
    Prev
    Next
    INDEX
    Explanations

    references to Roman-related topics or entities

    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
    459
    +0.13
    0.6%
    373
    +0.09
    0.4%
    209
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.02
    401
    +0.09
    0.02
    367
    +0.09
    0.02
    Negative Logits
    intosh
    -1.10
    olulu
    -0.78
    £ı
    -0.75
    lein
    -0.73
    eger
    -0.71
    ramid
    -0.70
    linger
    -0.68
    cham
    -0.67
    chief
    -0.67
    ickr
    -0.66
    POSITIVE LOGITS
     Catholic
    0.90
     Catholicism
    0.86
     Reign
    0.81
     legions
    0.78
     numer
    0.76
     Catholics
    0.75
     Torch
    0.74
    ians
    0.74
    omy
    0.72
    aldi
    0.72
    Activations Density 0.091%

    No Known Activations