Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 5768
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the importance of something or making statements about particular situations

    oai_token-act-pair · gpt-3.5-turbo

    the word "it" in various contexts, indicating a focus on statements related to general or abstract subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Peak
    -0.73
     Outside
    -0.72
    Outside
    -0.68
     Different
    -0.62
    Bott
    -0.62
    Different
    -0.62
    itaire
    -0.61
    eday
    -0.60
     Previous
    -0.58
    Intern
    -0.58
    POSITIVE LOGITS
     hereby
    0.83
    'll
    0.79
     largeDownload
    0.73
     nevertheless
    0.71
    wolf
    0.71
    wx
    0.70
    zbollah
    0.69
    tis
    0.68
    ctor
    0.68
    ald
    0.68
    Activations Density 0.202%

    No Known Activations