© 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. 10-RES-JB
    11. 17485
    Prev
    Next
    INDEX
    Explanations

    references to noble titles, specifically the title "Lord"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Lord."

    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
    ineries
    -0.73
    icides
    -0.69
    utic
    -0.68
     hoop
    -0.68
    akura
    -0.67
    iated
    -0.67
    ucha
    -0.66
    aeda
    -0.65
    ramid
    -0.64
    usp
    -0.64
    POSITIVE LOGITS
     Voldemort
    0.96
     Chancellor
    0.94
     Vader
    0.92
     Byron
    0.86
     Sandwich
    0.85
     Kelvin
    0.84
     Trafford
    0.84
     Chester
    0.83
     Paramount
    0.80
     Protector
    0.80
    Activations Density 0.020%

    No Known Activations