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. 11-RES-JB
    6. 15923
    Prev
    Next
    INDEX
    Explanations

    keywords related to comparisons and recommendations

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to various categories of items, particularly focusing on cards, clothing, and food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawdownloadcloneembedreportprint
    -0.77
    }:
    -0.66
    aughs
    -0.66
    olars
    -0.63
     Shutterstock
    -0.60
    Events
    -0.59
    ++++++++++++++++
    -0.59
    ||
    -0.59
    ģĸ
    -0.58
    uckles
    -0.57
    POSITIVE LOGITS
     containing
    1.14
    WithNo
    1.08
     consisting
    1.05
     whose
    1.00
     with
    1.00
     featuring
    1.00
     that
    1.00
     resembling
    0.99
     lacking
    0.96
     possessing
    0.95
    Activations Density 0.583%

    No Known Activations