© 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. 1-RES-JB
    11. 3816
    Prev
    Next
    INDEX
    Explanations

    acronyms related to organizational positions or legal matters

    oai_token-act-pair · gpt-3.5-turbo

    references to Freedom of Information (FOI) requests and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jenner
    -0.71
     Wilkinson
    -0.69
     Pul
    -0.67
     Nickel
    -0.65
     Powers
    -0.64
     Lith
    -0.63
     NHS
    -0.62
     Barcl
    -0.62
     defining
    -0.62
     cerebral
    -0.61
    POSITIVE LOGITS
    FO
    1.26
    LLOW
    1.14
    ogle
    0.97
    selage
    0.95
    gey
    0.90
    ortun
    0.90
    etus
    0.87
    obar
    0.87
    ove
    0.87
    ollower
    0.87
    Activations Density 0.003%

    No Known Activations