© 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. 9-RES-JB
    11. 11327
    Prev
    Next
    INDEX
    Explanations

    CSS attributes related to the width of elements

    oai_token-act-pair · gpt-3.5-turbo

    formatting indicators and dimension specifications in a layout context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opsis
    -0.84
    atis
    -0.81
    abul
    -0.72
    ophen
    -0.72
    odo
    -0.70
    asta
    -0.69
    osaurs
    -0.68
    assic
    -0.68
    ament
    -0.66
     Shore
    -0.65
    POSITIVE LOGITS
    s
    1.15
    sburg
    1.02
    sd
    0.83
    sr
    0.75
    heric
    0.74
    raltar
    0.71
    sg
    0.71
    urally
    0.65
    eenth
    0.64
    ible
    0.62
    Activations Density 0.151%

    No Known Activations