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. 13046
    Prev
    Next
    INDEX
    Explanations

    phrases related to philosophical ideologies and theories

    oai_token-act-pair · gpt-3.5-turbo

    references to important concepts, ideas, or symbols related to religion and philosophy

    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
     ADS
    -0.82
     Garmin
    -0.82
     Sammy
    -0.77
     Seah
    -0.77
     UFC
    -0.76
     Chattanooga
    -0.75
     Richie
    -0.73
     Wilmington
    -0.73
     Robbie
    -0.73
     ROCK
    -0.72
    POSITIVE LOGITS
    §
    1.10
    where
    1.03
    shall
    0.99
    whether
    0.99
    existence
    0.98
    âĶĢâĶĢâĶĢâĶĢ
    0.95
    ×Ķ
    0.92
    actual
    0.91
    ο
    0.91
     denotes
    0.91
    Activations Density 0.342%

    No Known Activations