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. 19492
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Slade"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Sl" followed by a number, indicating references to the "Slumdog Millionaire" movie or related terms

    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
    channelAvailability
    -0.83
     chi
    -0.82
    ERE
    -0.75
     PET
    -0.72
    aucus
    -0.72
    gio
    -0.70
    PET
    -0.69
     ammon
    -0.68
    emis
    -0.68
     pas
    -0.68
    POSITIVE LOGITS
     Sl
    3.56
    Sl
    2.39
    sl
    1.89
     sl
    1.64
     Slug
    1.62
     SL
    1.59
     Slave
    1.48
     Slide
    1.46
     Slip
    1.36
     Sk
    1.34
    Activations Density 0.013%

    No Known Activations