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. 7-RES-JB
    6. 10480
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a strong or emphatic statement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "no" and associated negation contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gypt
    -0.70
    ounded
    -0.68
    mud
    -0.66
    ounds
    -0.65
    abal
    -0.64
     tro
    -0.62
    oufl
    -0.61
    arthy
    -0.61
    MpServer
    -0.61
    etitive
    -0.61
    POSITIVE LOGITS
     sir
    0.97
     nor
    0.75
     thank
    0.71
    æĪ
    0.71
    onsense
    0.69
     kidding
    0.67
    nor
    0.67
     whatsoever
    0.65
    Shift
    0.64
     dear
    0.64
    Activations Density 0.055%

    No Known Activations