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. 21978
    Prev
    Next
    INDEX
    Explanations

    exclamations that typically express excitement or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    exclamation marks and expressions of excitement or enthusiasm

    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
     glim
    -0.75
     brig
    -0.72
     moss
    -0.72
     surpr
    -0.71
     defining
    -0.68
     manif
    -0.66
     arrang
    -0.66
     common
    -0.66
    undai
    -0.65
    awed
    -0.64
    POSITIVE LOGITS
    @#&
    1.50
    #$
    1.30
    @#
    1.09
    important
    0.99
    ?!
    0.98
     Euph
    0.96
     Brands
    0.86
     Somebody
    0.85
     Where
    0.83
     Featuring
    0.79
    Activations Density 0.060%

    No Known Activations