© 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. 2-RES-JB
    11. 7822
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Smith"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of names or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paragu
    -0.72
    cess
    -0.67
     ALS
    -0.66
    pty
    -0.66
     Dil
    -0.65
     diabetic
    -0.64
     Dalai
    -0.62
    condition
    -0.62
     Suk
    -0.61
     Libre
    -0.60
    POSITIVE LOGITS
    sonian
    1.52
    mith
    1.37
    smanship
    1.20
    doms
    1.03
    smith
    1.02
    son
    0.97
    sburg
    0.93
    intosh
    0.91
    ingen
    0.91
    shire
    0.88
    Activations Density 0.011%

    No Known Activations