© 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 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. 0-RES-JB
    11. 12909
    Prev
    Next
    INDEX
    Explanations

    phrases that are emphasized or noted as important in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "highlighted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atio
    -0.75
    aus
    -0.65
    mop
    -0.63
     fortun
    -0.62
     quarrel
    -0.61
    amus
    -0.61
    rel
    -0.61
     kin
    -0.61
    handle
    -0.60
     obe
    -0.60
    POSITIVE LOGITS
     highlighted
    3.32
     highlighting
    1.98
     undersc
    1.79
     highlight
    1.78
     highlights
    1.77
     showcased
    1.74
     outlined
    1.66
     emphasized
    1.59
     illustrated
    1.57
     flagged
    1.49
    Activations Density 0.016%

    No Known Activations