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. 2-RES-JB
    6. 19263
    Prev
    Next
    INDEX
    Explanations

    specific words that repeat consistently in the text like "para" and "Ana" and possibly the function patterns that link them together within the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "para" and variations related to certain contexts or themes, particularly in titles or sections of documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    士
    -0.87
    Ö¼
    -0.81
    esley
    -0.80
    ories
    -0.78
    sburg
    -0.76
    hardt
    -0.76
     Tycoon
    -0.72
    hart
    -0.70
    endor
    -0.70
    Reviewer
    -0.70
    POSITIVE LOGITS
     para
    0.98
     compr
    0.93
    forming
    0.82
    esthes
    0.80
     mosqu
    0.79
     tion
    0.78
     Karin
    0.76
     Suk
    0.76
    esthesia
    0.76
     pse
    0.75
    Activations Density 0.009%

    No Known Activations