© 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. 12170
    Prev
    Next
    INDEX
    Explanations

    the phrase "that is" followed by describing a characteristic or condition

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases introducing clauses that specify conditions or characteristics

    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
    iddler
    -0.74
    window
    -0.66
    case
    -0.63
    istance
    -0.63
    peed
    -0.59
    wheel
    -0.59
    instance
    -0.58
    onica
    -0.58
    icut
    -0.58
    umar
    -0.57
    POSITIVE LOGITS
     wors
    1.15
     relies
    1.12
     lacks
    1.10
     celebrates
    1.09
     refuses
    1.07
     loves
    1.04
     hates
    1.03
     strives
    1.02
     este
    1.01
     boasts
    1.00
    Activations Density 0.145%

    No Known Activations