© 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. 21118
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming syntax and features

    oai_token-act-pair · gpt-3.5-turbo

    terms related to devices and technical specifications

    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
    arnaev
    -0.78
     Flavoring
    -0.73
    qua
    -0.71
    igh
    -0.68
    utics
    -0.66
     Believe
    -0.66
    rolet
    -0.66
     Murd
    -0.66
    utic
    -0.66
     Fifth
    -0.64
    POSITIVE LOGITS
     name
    1.29
     identifier
    1.27
     IDs
    1.20
    Name
    1.20
     names
    1.19
     description
    1.14
     selector
    1.12
     ID
    1.09
    NAME
    1.09
     descriptions
    1.09
    Activations Density 0.309%

    No Known Activations