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. 9-RES-JB
    6. 11790
    Prev
    Next
    INDEX
    Explanations

    phrases enclosed in quotation marks, potentially indicating direct speech or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly quotation marks and periods, indicating dialogue or the end of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Shot
    -0.71
    ĻĤ
    -0.64
    kw
    -0.64
     Shot
    -0.63
    ensical
    -0.63
    eka
    -0.62
    uberty
    -0.61
    iaries
    -0.61
     prenatal
    -0.60
     Kut
    -0.60
    POSITIVE LOGITS
    [
    0.71
     ie
    0.70
     (£
    0.65
    £
    0.64
    estone
    0.62
    piece
    0.59
    VID
    0.59
    hoe
    0.59
     Whilst
    0.57
    ãħĭ
    0.57
    Activations Density 0.051%

    No Known Activations