© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 10523
    Prev
    Next
    INDEX
    Explanations

    names of individuals and families

    oai_token-act-pair · gpt-3.5-turbo

    names of people and families involved in notable cases

    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
     Nasa
    -0.66
    olulu
    -0.64
    terday
    -0.63
    posted
    -0.61
    isconsin
    -0.59
    asionally
    -0.58
     seism
    -0.57
    cigarettes
    -0.56
    pelled
    -0.56
    )=(
    -0.56
    POSITIVE LOGITS
     brothers
    1.42
     sisters
    1.28
     Brothers
    1.25
     family
    1.24
     clan
    1.12
     Family
    1.09
     twins
    1.04
     siblings
    1.03
    seys
    0.98
    aughs
    0.97
    Activations Density 0.277%

    No Known Activations