© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 17188
    Prev
    Next
    INDEX
    Explanations

    phrases related to software development and programming concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating levels of quality or intensity

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Investigative
    -0.52
     Faul
    -0.52
     Prosecut
    -0.51
     Democratic
    -0.51
     Workers
    -0.50
    CNN
    -0.49
     Political
    -0.48
    resa
    -0.47
     Hezbollah
    -0.47
     Cong
    -0.47
    POSITIVE LOGITS
     haha
    0.70
     XD
    0.63
     devs
    0.63
     ;)
    0.62
     kinda
    0.61
     lol
    0.57
    acly
    0.56
     :)
    0.56
     vibe
    0.55
    acters
    0.54
    Activations Density 4.376%

    No Known Activations