© 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. 18990
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Steven"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Steven" across various contexts

    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
    LOAD
    -0.77
    teen
    -0.72
    cffffcc
    -0.65
     supreme
    -0.61
    eer
    -0.61
    fect
    -0.60
    req
    -0.60
     circ
    -0.59
    hops
    -0.58
    agonist
    -0.58
    POSITIVE LOGITS
     Spielberg
    1.23
    sonian
    1.20
     Gerrard
    1.07
     Moff
    1.00
    herty
    0.99
     Avery
    0.98
     Mn
    0.94
     Hawking
    0.92
     Universe
    0.81
     Stam
    0.79
    Activations Density 0.015%

    No Known Activations