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. 11692
    Prev
    Next
    INDEX
    Explanations

    mentions of specific titles, particularly related to movies and shows

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and titles related to various forms of media and personal experiences

    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
     themselves
    -0.86
     Himself
    -0.77
     himself
    -0.70
     yourselves
    -0.70
     headquartered
    -0.65
    ributes
    -0.64
    Their
    -0.63
     prominently
    -0.63
    arnaev
    -0.60
    idates
    -0.60
    POSITIVE LOGITS
     colleague
    1.10
     myself
    0.96
    husband
    0.93
     friends
    0.93
     roommate
    0.92
     friend
    0.90
     buddies
    0.89
    favorite
    0.89
     girlfriend
    0.88
     buddy
    0.88
    Activations Density 0.300%

    No Known Activations