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. 7-RES-JB
    6. 17004
    Prev
    Next
    INDEX
    Explanations

    historical time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to centuries, particularly in a historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vec
    -0.70
     juggling
    -0.65
    utical
    -0.63
     Powder
    -0.62
    EStream
    -0.62
     destro
    -0.62
     DRAG
    -0.62
    nels
    -0.61
     additive
    -0.61
     Paradox
    -0.61
    POSITIVE LOGITS
    century
    1.27
    eyed
    1.01
    hour
    0.98
    favorite
    0.95
    level
    0.91
    grade
    0.90
    degree
    0.89
    dimensional
    0.89
    inch
    0.88
    party
    0.85
    Activations Density 0.063%

    No Known Activations