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. 13001
    Prev
    Next
    INDEX
    Explanations

    technical descriptions or explanations

    oai_token-act-pair · gpt-3.5-turbo

    the word "describe" and its variations, indicating descriptions or explanations of concepts and phenomena

    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
    ild
    -0.78
    é¾įå
    -0.74
    osate
    -0.70
    uyomi
    -0.69
    youtube
    -0.68
    Tickets
    -0.68
    Lex
    -0.68
    ©¶æ¥µ
    -0.67
    assic
    -0.67
    lua
    -0.66
    POSITIVE LOGITS
     how
    1.20
     aspects
    1.02
     what
    0.98
     everything
    0.96
     behaviors
    0.89
    enance
    0.87
     exactly
    0.86
     anything
    0.86
     situations
    0.83
     behaviours
    0.82
    Activations Density 0.208%

    No Known Activations