© 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. 2813
    Prev
    Next
    INDEX
    Explanations

    mentions of characters or entities names ending with 'er'

    oai_token-act-pair · gpt-3.5-turbo

    words associated with sensory perceptions such as sight and smell

    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
     Ide
    -0.71
     Alleg
    -0.64
     Trib
    -0.64
     cad
    -0.63
     congr
    -0.63
     triangle
    -0.63
    ãĥł
    -0.61
     Courts
    -0.61
     Ezek
    -0.60
     respons
    -0.60
    POSITIVE LOGITS
    glers
    1.01
    kered
    0.93
    erville
    0.86
    iland
    0.85
    rill
    0.84
    bley
    0.84
    aker
    0.84
    etsk
    0.84
    lda
    0.80
    lesh
    0.78
    Activations Density 0.081%

    No Known Activations