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. 21832
    Prev
    Next
    INDEX
    Explanations

    phrases related to delivery services or locations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to delivery, shipping, and harbor projects

    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
     tract
    -0.77
     repe
    -0.73
     tracts
    -0.72
     pursuits
    -0.72
     rever
    -0.72
     bas
    -0.71
     regress
    -0.71
     blues
    -0.70
     routine
    -0.69
     triangle
    -0.69
    POSITIVE LOGITS
     Delivery
    2.18
     Shipping
    2.09
     Construction
    1.88
     Harbour
    1.81
     Publishing
    1.61
    Construction
    1.36
    Delivery
    1.22
    Shipping
    1.15
     Enterprises
    1.12
    conn
    1.11
    Activations Density 0.042%

    No Known Activations