© 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. 3-RES-JB
    11. 20076
    Prev
    Next
    INDEX
    Explanations

    abbreviations/acronyms related to official organizations

    oai_token-act-pair · gpt-3.5-turbo

    acronyms or abbreviations related to organizations and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    es
    -0.89
    rick
    -0.86
    ord
    -0.83
    aghan
    -0.82
    thouse
    -0.81
    roman
    -0.80
    mar
    -0.78
    este
    -0.78
    bal
    -0.77
    jah
    -0.77
    POSITIVE LOGITS
    ICS
    1.45
    FORM
    1.32
    WAYS
    1.31
    ANCE
    1.29
    IST
    1.28
    IFIED
    1.28
    ILS
    1.26
    IDER
    1.25
    ADA
    1.25
    IUM
    1.24
    Activations Density 0.050%

    No Known Activations