© 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. 5329
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal opinions or feelings

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "I can."

    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
    furt
    -0.75
    ãĤ¼
    -0.68
    soever
    -0.66
    pires
    -0.66
    bats
    -0.65
    cedes
    -0.62
    achu
    -0.62
    soDeliveryDate
    -0.60
    Board
    -0.59
     Critics
    -0.59
    POSITIVE LOGITS
    't
    1.52
     attest
    1.42
     assure
    1.39
     confirm
    1.14
     guarantee
    1.14
     honestly
    1.11
     imagine
    1.10
     tell
    1.07
     confidently
    1.07
     understand
    1.06
    Activations Density 0.067%

    No Known Activations