© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 1353
    Prev
    Next
    INDEX
    Explanations

    legal disclaimer statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to copyright and restrictions on content usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naire
    -0.70
     Hann
    -0.67
     Humanity
    -0.65
     Emin
    -0.64
    naires
    -0.64
     Tsukuyomi
    -0.63
     wonder
    -0.63
    inguished
    -0.59
    ngth
    -0.58
     sweets
    -0.57
    POSITIVE LOGITS
    Cop
    0.70
    Republic
    0.70
    Unless
    0.70
     iP
    0.69
     nor
    0.67
     redistributed
    0.67
    ificial
    0.67
    Catal
    0.65
     unless
    0.65
     Printed
    0.64
    Activations Density 0.055%

    No Known Activations