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. 6685
    Prev
    Next
    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating locations or purposes for various facilities or gatherings

    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
    chrome
    -0.67
    doi
    -0.66
    peat
    -0.65
    holes
    -0.64
    aan
    -0.64
    Adds
    -0.63
    Blade
    -0.63
     undone
    -0.61
    Scope
    -0.60
    eus
    -0.60
    POSITIVE LOGITS
     storing
    0.99
     sale
    0.91
     foreigners
    0.82
     pilgrims
    0.82
     travelers
    0.82
     tourists
    0.81
     transporting
    0.81
     guests
    0.81
     hire
    0.80
     hikers
    0.79
    Activations Density 0.190%

    No Known Activations