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. 6-RES-JB
    6. 6789
    Prev
    Next
    INDEX
    Explanations

    declarative sentences ending with some form of punctuation like a period, question mark, or exclamation point

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods, exclamation points, and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eatures
    -0.82
    eteenth
    -0.81
     encount
    -0.80
    awei
    -0.78
     estates
    -0.77
    awed
    -0.76
    itionally
    -0.72
    eatured
    -0.71
     positioning
    -0.71
     uncommon
    -0.71
    POSITIVE LOGITS
     Somebody
    1.12
     Especially
    1.11
     Please
    1.10
     Everybody
    1.06
     Where
    1.04
     Anyway
    1.02
     Anything
    1.02
     That
    1.02
     Didn
    1.01
     Whoever
    1.01
    Activations Density 0.281%

    No Known Activations