© 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 EvalsExportsinterp-engineNEWAPI 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. 15166
    Prev
    Next
    INDEX
    Explanations

    acronyms related to postal services

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations or institutions

    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
     bills
    -0.64
     Radeon
    -0.62
     gir
    -0.61
     Rusty
    -0.59
     Mali
    -0.59
    essed
    -0.59
     ages
    -0.59
     virginity
    -0.58
     Heard
    -0.57
     Melt
    -0.57
    POSITIVE LOGITS
    PO
    4.46
     PO
    2.14
    Po
    1.54
    PE
    1.52
    PI
    1.40
    po
    1.39
    SO
    1.34
    POS
    1.31
    CO
    1.27
    MO
    1.26
    Activations Density 0.014%

    No Known Activations