© 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. 10-RES-JB
    11. 18803
    Prev
    Next
    INDEX
    Explanations

    phrases related to business chambers or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to various chambers of commerce

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wass
    -0.66
     Mandela
    -0.60
     APR
    -0.57
     Scion
    -0.56
     curfew
    -0.56
     Scotia
    -0.55
    ces
    -0.55
     expectancy
    -0.54
     Stalin
    -0.54
     SCHOOL
    -0.54
    POSITIVE LOGITS
    lain
    1.63
    maid
    1.09
    flies
    0.84
    pit
    0.84
    house
    0.82
    piece
    0.81
     chambers
    0.79
    men
    0.79
    itone
    0.78
     chamber
    0.77
    Activations Density 0.051%

    No Known Activations