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. 19267
    Prev
    Next
    INDEX
    Explanations

    sentences ending in a strong and conclusive manner

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending with periods

    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
     satell
    -1.03
    quartered
    -0.87
    ascus
    -0.87
     mosqu
    -0.85
     nodd
    -0.83
    undai
    -0.83
     notor
    -0.83
     dimensional
    -0.82
     challeng
    -0.82
     confir
    -0.80
    POSITIVE LOGITS
     ..."
    1.26
     âĢİ
    1.20
     Photograph
    1.20
     [/
    1.20
     —
    1.18
     Especially
    1.17
     That
    1.15
     Unless
    1.14
     Instead
    1.13
     âĢº
    1.12
    Activations Density 0.374%

    No Known Activations