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. 3-RES-JB
    6. 21805
    Prev
    Next
    INDEX
    Explanations

    mentions of the singer-songwriter "Weezer"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions or references to "Weezer" throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.78
     Icelandic
    -0.68
     Cath
    -0.67
     Commonwealth
    -0.66
     latitude
    -0.65
     Kerala
    -0.65
     canopy
    -0.63
     Glou
    -0.63
     glim
    -0.62
     Malays
    -0.62
    POSITIVE LOGITS
    ombie
    1.18
    eta
    1.03
    hao
    1.03
    ombies
    1.01
    ez
    1.00
    edo
    0.97
    hov
    0.97
    ymes
    0.95
    arella
    0.93
    cellent
    0.92
    Activations Density 0.008%

    No Known Activations