© 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. 0-RES-JB
    11. 8270
    Prev
    Next
    INDEX
    Explanations

    URL sources

    oai_token-act-pair · gpt-3.5-turbo

    sources or references in structured data or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inctions
    -0.77
     mushroom
    -0.73
     Rabb
    -0.65
     Royal
    -0.64
     hors
    -0.64
     reservations
    -0.64
     award
    -0.62
     ceremonial
    -0.61
     reservation
    -0.60
     invite
    -0.60
    POSITIVE LOGITS
    src
    4.47
     src
    2.75
    Contents
    1.32
     dst
    1.22
    source
    1.18
    href
    1.14
    Source
    1.06
    Origin
    1.03
    origin
    1.02
    runtime
    0.97
    Activations Density 0.015%

    No Known Activations