Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 16158
    Prev
    Next
    INDEX
    Explanations

    financial terms relating to pensions and retirement

    oai_token-act-pair · gpt-3.5-turbo

    details related to pension funds and financial transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.99
     Whitman
    -0.92
    Atlanta
    -0.92
     Theater
    -0.91
     halftime
    -0.88
     colors
    -0.87
     theater
    -0.86
    caliber
    -0.86
     Exhibit
    -0.84
     Anaheim
    -0.84
    POSITIVE LOGITS
     NHS
    1.42
     £
    1.42
     incap
    1.38
     recognised
    1.34
     Britons
    1.29
    Scotland
    1.27
     organisations
    1.26
     UK
    1.26
     Trave
    1.25
     authorised
    1.24
    Activations Density 0.585%

    No Known Activations