© 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. 11-RES-JB
    11. 2345
    Prev
    Next
    INDEX
    Explanations

    phrases related to official or formal statements or announcements

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific symbol or character repeatedly in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ABE
    -0.66
     MU
    -0.62
    sters
    -0.62
     Manz
    -0.61
     Shelter
    -0.60
     weap
    -0.60
    ozy
    -0.59
     Tanzania
    -0.58
     Belg
    -0.58
     RAD
    -0.58
    POSITIVE LOGITS
    ª
    1.44
    Ĵ
    1.41
    IJ
    1.34
    ĸ
    1.25
    ı
    1.25
    ¤
    1.23
    į
    1.22
    ¬
    1.21
    Ķ
    1.21
    ł
    1.20
    Activations Density 0.107%

    No Known Activations