© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 20966
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals, particularly surnames

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly focusing on certain last names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terior
    -0.70
    places
    -0.69
     port
    -0.68
    izen
    -0.66
    erences
    -0.66
    onyms
    -0.64
    isu
    -0.64
    ebus
    -0.63
     ports
    -0.63
    lator
    -0.63
    POSITIVE LOGITS
     Higgins
    1.19
     Wiggins
    0.97
     Saunders
    0.97
     Browne
    0.89
    aunders
    0.87
     Cummings
    0.87
     Lans
    0.83
    loo
    0.81
     Scully
    0.80
     Colomb
    0.77
    Activations Density 0.006%

    No Known Activations