© 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. 9-RES-JB
    11. 10147
    Prev
    Next
    INDEX
    Explanations

    YouTube video links

    oai_token-act-pair · gpt-3.5-turbo

    video identifiers and links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mushrooms
    -0.66
     battered
    -0.62
     specialists
    -0.62
     Lovecraft
    -0.60
     bis
    -0.59
     womb
    -0.59
     rallies
    -0.59
     apolog
    -0.59
     signs
    -0.58
     wonders
    -0.58
    POSITIVE LOGITS
    =
    1.49
    =-
    1.24
    =$
    1.18
    =/
    1.16
    =[
    1.08
    ={
    1.02
    =\"
    0.96
    ='
    0.95
    =#
    0.92
    =(
    0.90
    Activations Density 0.047%

    No Known Activations