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. 7-RES-JB
    6. 15977
    Prev
    Next
    INDEX
    Explanations

    references to mythical and fantastical elements

    oai_token-act-pair · gpt-3.5-turbo

    references to power struggles and conflicts in a fictional narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zucker
    -0.94
     bumper
    -0.79
     MSNBC
    -0.75
     golf
    -0.74
    estyle
    -0.74
     Carney
    -0.73
    ilater
    -0.73
     Rubio
    -0.73
    Photo
    -0.72
    Article
    -0.72
    POSITIVE LOGITS
     sorce
    1.23
     mages
    1.19
     Aether
    1.19
     sorcerer
    1.18
     Norn
    1.15
     Sorce
    1.12
     orcs
    1.11
     Inquisitor
    1.11
     mage
    1.09
     nobles
    1.09
    Activations Density 1.454%

    No Known Activations