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. 11-RES-JB
    6. 15558
    Prev
    Next
    INDEX
    Explanations

    expressions of opinions or stances on various topics

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant public commentary or statements made by various individuals

    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
     Transactions
    -0.78
    aughtered
    -0.75
    artifacts
    -0.73
     Reincarnated
    -0.70
     Procedures
    -0.68
     Records
    -0.68
     Committees
    -0.67
     Printed
    -0.66
    halla
    -0.66
     Borders
    -0.65
    POSITIVE LOGITS
     succinct
    1.27
     eloqu
    1.23
     scathing
    1.18
     insightful
    1.18
     poignant
    1.18
     fascinating
    1.12
     enlight
    1.12
     compelling
    1.08
     chilling
    1.08
     startling
    1.06
    Activations Density 0.196%

    No Known Activations