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. 3284
    Prev
    Next
    INDEX
    Explanations

    phrases related to government policies or decisions

    oai_token-act-pair · gpt-3.5-turbo

    components related to plans, decisions, and legal matters

    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
    caliber
    -0.78
     behaviors
    -0.75
     harbor
    -0.75
     traveling
    -0.73
    plet
    -0.73
     Myr
    -0.72
     neighboring
    -0.71
    izers
    -0.71
     colorful
    -0.70
    adena
    -0.70
    POSITIVE LOGITS
     recognised
    1.30
     envis
    1.24
     emphas
    1.24
     £
    1.21
     centres
    1.20
     Nato
    1.18
     criticised
    1.17
     recognise
    1.15
     Labour
    1.14
     recogn
    1.14
    Activations Density 0.396%

    No Known Activations