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. 10398
    Prev
    Next
    INDEX
    Explanations

    phrases related to urgency or action

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that include punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Period at the end of extremely short sentences.

    Explanation Uploaded by User

    periods after sentence fragments

    Explanation Uploaded by User
    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
     advoc
    -0.81
     encount
    -0.77
     notor
    -0.72
     withd
    -0.71
     volunte
    -0.71
     emanc
    -0.71
    icz
    -0.70
    uly
    -0.68
    eatured
    -0.68
     inver
    -0.68
    POSITIVE LOGITS
     Literally
    1.12
     Anyway
    1.10
     Kills
    1.05
     Seriously
    1.03
     Lots
    1.03
     Especially
    1.02
     And
    0.97
     Everybody
    0.96
     Everywhere
    0.95
     Nothing
    0.95
    Activations Density 0.411%

    No Known Activations