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. 10-RES-JB
    6. 1479
    Prev
    Next
    INDEX
    Explanations

    email addresses and social media handles related to news outlets and journalists

    oai_token-act-pair · gpt-3.5-turbo

    references to specific media outlets or social media handles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Directive
    -0.81
     Scheme
    -0.77
     Reduction
    -0.73
     Pupp
    -0.72
     Jungle
    -0.71
     Sale
    -0.70
     Loving
    -0.68
     Suit
    -0.67
     Shame
    -0.67
     Mock
    -0.67
    POSITIVE LOGITS
    news
    1.01
    archives
    0.94
    journal
    0.93
    crim
    0.91
    abc
    0.91
    medi
    0.89
    daily
    0.88
    weekly
    0.88
    media
    0.88
    monitor
    0.87
    Activations Density 0.059%

    No Known Activations