Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22021
    Prev
    Next
    INDEX
    Explanations

    the name 'Jude'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jude" and its context

    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
     Shields
    -0.72
     Croat
    -0.71
     Durham
    -0.70
    culus
    -0.68
    hooting
    -0.67
     clutch
    -0.67
    prising
    -0.65
    Atlanta
    -0.65
    acs
    -0.65
     Atlanta
    -0.65
    POSITIVE LOGITS
     Jude
    3.76
     Galile
    1.45
     Fay
    1.18
     Mae
    1.15
     bye
    1.01
    olen
    0.99
     Dee
    0.99
     Jud
    0.99
     Ike
    0.95
     Rae
    0.93
    Activations Density 0.048%

    No Known Activations