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. 10677
    Prev
    Next
    INDEX
    Explanations

    content that is structured in a particular format or template

    oai_token-act-pair · gpt-3.5-turbo

    specific symbols or unique characters

    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
     disadvant
    -0.70
     bankrupt
    -0.63
     improperly
    -0.62
     inconsist
    -0.61
     unrecogn
    -0.61
     conduc
    -0.61
     phased
    -0.61
     thwarted
    -0.60
     incent
    -0.59
     disadvantage
    -0.59
    POSITIVE LOGITS
    ï¸ı
    1.10
    here
    1.00
    are
    0.93
    we
    0.91
    there
    0.91
     denotes
    0.89
    shall
    0.87
    comes
    0.85
    is
    0.83
    shows
    0.83
    Activations Density 0.065%

    No Known Activations