© 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. 3369
    Prev
    Next
    INDEX
    Explanations

    words related to scientific concepts and technical terms, particularly in physics and biology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical or scientific properties and classifications

    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
     arrogance
    -0.71
     mock
    -0.71
     complaining
    -0.70
     Therapy
    -0.69
     couch
    -0.69
     envy
    -0.68
     approve
    -0.68
     stew
    -0.67
     wont
    -0.65
     frustration
    -0.64
    POSITIVE LOGITS
    itudinal
    1.05
    onal
    1.05
    otropic
    1.05
    ogeneous
    1.00
    olar
    1.00
    omorphic
    1.00
    ucle
    0.99
    atern
    0.98
    llular
    0.97
    onic
    0.97
    Activations Density 0.170%

    No Known Activations