© 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. 7-RES-JB
    11. 23912
    Prev
    Next
    INDEX
    Explanations

    HTML or programming code snippets with particular patterns or components

    oai_token-act-pair · gpt-3.5-turbo

    tokens related to programming or script syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atform
    -0.95
     Manson
    -0.66
     STE
    -0.65
    ciating
    -0.65
    xon
    -0.64
     Pearce
    -0.64
     orche
    -0.64
     Anita
    -0.63
    ulhu
    -0.63
    iasis
    -0.63
    POSITIVE LOGITS
    taboola
    1.07
    chance
    0.90
    blank
    0.90
    default
    0.85
    nom
    0.85
    main
    0.84
    tra
    0.81
    train
    0.80
    self
    0.80
    EStreamFrame
    0.79
    Activations Density 0.020%

    No Known Activations