© 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 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. 8-RES-JB
    11. 19372
    Prev
    Next
    INDEX
    Explanations

    software-related terms, such as file dependencies, libraries, applications, and repositories

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to software dependencies and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rontal
    -0.64
    cffffcc
    -0.62
    atorium
    -0.62
     Travels
    -0.58
     Durham
    -0.57
    liction
    -0.54
     Patriot
    -0.54
    phas
    -0.54
    pter
    -0.54
     Telegram
    -0.54
    POSITIVE LOGITS
    paces
    1.36
    pace
    1.27
    hips
    1.20
    mith
    1.14
    ystem
    1.12
    hip
    1.11
    ources
    1.08
    etting
    1.02
    ets
    1.02
    ettings
    1.01
    Activations Density 0.381%

    No Known Activations