© 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. 2-RES-JB
    11. 19748
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically the name "Kent"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kent" and its variations

    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
    xual
    -0.92
    thood
    -0.82
    BOOK
    -0.76
    SHIP
    -0.70
    llah
    -0.70
    mble
    -0.69
     behavi
    -0.69
    sbm
    -0.68
    */(
    -0.68
    unknown
    -0.67
    POSITIVE LOGITS
     Kent
    1.13
    rell
    0.92
     Dover
    0.86
    ucky
    0.83
     Walton
    0.82
     Somers
    0.81
     Cooke
    0.80
     Baz
    0.79
    Kent
    0.78
    wood
    0.75
    Activations Density 0.004%

    No Known Activations