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. 0-RES-JB
    6. 19722
    Prev
    Next
    INDEX
    Explanations

    words related to thrilling and exciting experiences or activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "adventure" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cohen
    -0.77
     Gins
    -0.72
    Sign
    -0.71
    partial
    -0.71
     Regist
    -0.68
    stem
    -0.67
     Thomson
    -0.65
    sign
    -0.65
    eto
    -0.64
     Shea
    -0.64
    POSITIVE LOGITS
     adventure
    3.55
     adventures
    2.65
     Adventure
    2.19
    Adventure
    2.16
     adventurer
    1.82
    venture
    1.72
     adventurers
    1.64
     expedition
    1.58
     Adventures
    1.56
     adventurous
    1.50
    Activations Density 0.023%

    No Known Activations