© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 5527
    Prev
    Next
    INDEX
    Explanations

    file extensions and related technical terms

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and formatting that signal the structure of written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sle
    -0.44
     subdiv
    -0.42
     computer
    -0.41
     Bolt
    -0.41
     refere
    -0.40
     flo
    -0.40
     controlled
    -0.40
     swe
    -0.39
     grou
    -0.39
     snap
    -0.39
    POSITIVE LOGITS
    Translation
    0.65
    Thus
    0.61
    Facebook
    0.58
    ³³³³³³³³³³³³³³³³
    0.58
    Such
    0.57
    Meanwhile
    0.56
    Advertisement
    0.56
    Much
    0.56
    Ultimately
    0.56
    Writing
    0.55
    Activations Density 0.865%

    No Known Activations