© 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. 12625
    Prev
    Next
    INDEX
    Explanations

    the word "Lucas 9" specifically

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Lucas" or references related to entities associated with that name

    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
    ãĥĥãĥĪ
    -0.74
    eering
    -0.69
    gettable
    -0.67
    orget
    -0.67
    req
    -0.66
    ħĭ
    -0.65
    lying
    -0.64
    BOOK
    -0.64
    gencies
    -0.63
    irements
    -0.63
    POSITIVE LOGITS
    film
    1.13
     Lucas
    1.12
     Skywalker
    1.01
    Film
    0.98
    Luc
    0.83
     Browne
    0.78
    avin
    0.76
    ious
    0.75
     Bros
    0.75
    Fan
    0.74
    Activations Density 0.004%

    No Known Activations