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. 9405
    Prev
    Next
    INDEX
    Explanations

    words related to technical systems, certificates, and methods like "system," "key," "Alert," "Bus," "Role," "value," "suppression," "education," and "backend" from the given text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to systems, structures, and components of organization

    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
     Harley
    -0.93
    pard
    -0.90
     Kendrick
    -0.90
    fur
    -0.89
     Haram
    -0.88
    isconsin
    -0.86
     Spiegel
    -0.85
     Ange
    -0.84
    ÄŁ
    -0.84
     Dunk
    -0.83
    POSITIVE LOGITS
     system
    1.91
     systems
    1.80
    system
    1.70
     System
    1.60
     SYSTEM
    1.59
     subsystem
    1.53
    System
    1.50
     Systems
    1.43
    ystem
    1.32
     mechanism
    1.28
    Activations Density 0.293%

    No Known Activations