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. 8-RES-JB
    6. 8840
    Prev
    Next
    INDEX
    Explanations

    quotes in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of quoted speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parting
    -0.84
     periodic
    -0.79
     brid
    -0.77
     favor
    -0.77
     dispos
    -0.77
     adjud
    -0.76
     confir
    -0.76
     scheduled
    -0.73
     dispar
    -0.73
     sway
    -0.72
    POSITIVE LOGITS
    They
    1.50
    We
    1.46
    It
    1.45
    Especially
    1.45
    I
    1.44
    Nobody
    1.43
    Because
    1.42
    Everybody
    1.40
    But
    1.38
    You
    1.35
    Activations Density 0.108%

    No Known Activations