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. 6-RES-JB
    6. 14362
    Prev
    Next
    INDEX
    Explanations

    references to buses

    oai_token-act-pair · gpt-3.5-turbo

    references to buses and public transportation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sson
    -0.72
     marrow
    -0.70
     Martial
    -0.66
    aneous
    -0.63
     Centauri
    -0.63
     Christensen
    -0.63
     accur
    -0.62
    arial
    -0.61
    vironment
    -0.59
    nesota
    -0.59
    POSITIVE LOGITS
    loads
    1.25
    load
    1.12
    boys
    0.97
    hel
    0.96
    INESS
    0.93
    boy
    0.83
    kers
    0.82
    hell
    0.79
    hy
    0.79
    inson
    0.78
    Activations Density 0.018%

    No Known Activations