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. 19377
    Prev
    Next
    INDEX
    Explanations

    numerical data related to percentage increase and growth

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data and statistics relating to increases or changes over time

    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
    galitarian
    -0.70
    sonian
    -0.67
     bob
    -0.66
    Rand
    -0.61
     arbit
    -0.60
    bart
    -0.60
    Reviewer
    -0.58
    Ĥª
    -0.56
    externalActionCode
    -0.56
     resemb
    -0.55
    POSITIVE LOGITS
     previous
    1.19
     prior
    1.11
     2009
    0.97
     last
    0.96
     2014
    0.96
     2013
    0.96
     2011
    0.95
     2008
    0.94
     preceding
    0.93
     2015
    0.92
    Activations Density 0.158%

    No Known Activations