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. 11-RES-JB
    6. 10927
    Prev
    Next
    INDEX
    Explanations

    specific time-related expressions

    oai_token-act-pair · gpt-3.5-turbo

    references to time and performance metrics

    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
    ĸļ
    -0.59
     condol
    -0.58
     1886
    -0.56
     apologies
    -0.54
     Leilan
    -0.52
     condolences
    -0.51
     365
    -0.50
     1888
    -0.49
     1919
    -0.48
     1861
    -0.48
    POSITIVE LOGITS
    idding
    0.57
    asure
    0.51
    fire
    0.51
    ãĤĬ
    0.50
    ª
    0.49
    Place
    0.49
    vertising
    0.49
    paying
    0.49
    ãĥīãĥ©
    0.48
    ale
    0.47
    Activations Density 0.736%

    No Known Activations