© 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. 4-RES-JB
    11. 563
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and specific entities in the text

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

    No Comments

    Negative Logits
    minist
    -0.77
    arded
    -0.75
    emetery
    -0.74
    inct
    -0.74
    semb
    -0.73
    amily
    -0.72
    ffe
    -0.72
    artment
    -0.71
    orpor
    -0.70
    chemist
    -0.70
    POSITIVE LOGITS
     Cody
    0.84
     Dickinson
    0.83
    eers
    0.75
    halla
    0.73
    SHIP
    0.72
    ilater
    0.71
    birds
    0.71
     Vaughn
    0.71
     Kodi
    0.70
    MENTS
    0.69
    Activations Density 0.026%

    No Known Activations