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. 8932
    Prev
    Next
    INDEX
    Explanations

    references to tables and appendices within a document

    oai_token-act-pair · gpt-3.5-turbo

    references to tables and appendices in a document

    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
    akuya
    -0.79
     denies
    -0.70
     hung
    -0.70
     camer
    -0.69
     hangs
    -0.68
     justice
    -0.68
    onz
    -0.67
     obsc
    -0.67
    dk
    -0.67
    jin
    -0.66
    POSITIVE LOGITS
     Table
    3.80
    Table
    3.39
     Tables
    2.59
     TABLE
    2.41
    TABLE
    2.40
    table
    2.39
     table
    2.30
     tables
    2.00
     Figure
    1.92
     Fig
    1.56
    Activations Density 0.012%

    No Known Activations