© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 7375
    Prev
    Next
    INDEX
    Explanations

    news websites, social media handles, and email addresses with a particular focus on the San Francisco Chronicle and Washington Post

    oai_token-act-pair · gpt-3.5-turbo

    references to media outlets or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Train
    -0.74
     Gamble
    -0.73
     Mock
    -0.73
     Scheme
    -0.73
     Stall
    -0.72
     Supplemental
    -0.72
     Pupp
    -0.71
     Versus
    -0.71
     Jade
    -0.70
     Loving
    -0.70
    POSITIVE LOGITS
    journal
    1.07
    archives
    1.02
    media
    1.00
    news
    0.96
    foundation
    0.94
    abc
    0.94
    medi
    0.92
    yahoo
    0.91
    weekly
    0.91
    library
    0.91
    Activations Density 0.069%

    No Known Activations