© 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 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. 0-RES-JB
    11. 9965
    Prev
    Next
    INDEX
    Explanations

    names and surnames, particularly the surname "Porter."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly the name "Porter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fib
    -0.69
     atom
    -0.68
    angs
    -0.67
     atoms
    -0.67
    cry
    -0.66
    Cy
    -0.63
     Î
    -0.63
     domain
    -0.63
     mitochond
    -0.62
     hiber
    -0.62
    POSITIVE LOGITS
     Porter
    4.05
     Stout
    1.64
     Powell
    1.31
     Morton
    1.30
    orter
    1.24
     McGee
    1.18
     Otto
    1.16
     Painter
    1.08
    porter
    1.04
     Bradley
    1.03
    Activations Density 0.016%

    No Known Activations