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. 11-RES-JB
    6. 15565
    Prev
    Next
    INDEX
    Explanations

    strings of text ending with a special character "Ċ" followed by a numeric value indicating the strength of activation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize strong emotions or personal preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fu
    -0.66
     flats
    -0.61
    senal
    -0.59
     Alb
    -0.59
     manned
    -0.59
     wearer
    -0.56
     Skydragon
    -0.56
     Hispan
    -0.55
     Racer
    -0.55
     mansion
    -0.54
    POSITIVE LOGITS
    assian
    0.83
    ↵
    0.81
    DragonMagazine
    0.79
    until
    0.78
    ³³³
    0.77
    database
    0.75
    termin
    0.74
    ̶
    0.74
    ³³³³³³³³³³³³³³³³
    0.74
    til
    0.73
    Activations Density 0.180%

    No Known Activations