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. 4300
    Prev
    Next
    INDEX
    Explanations

    keywords indicating different scenarios or options being considered

    oai_token-act-pair · gpt-3.5-turbo

    the word "whether."

    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
    ioxide
    -0.69
    aez
    -0.69
    visors
    -0.69
    isi
    -0.67
    atari
    -0.66
    oos
    -0.66
    unch
    -0.62
    ovember
    -0.62
    atches
    -0.62
    ãĥ´ãĤ¡
    -0.61
    POSITIVE LOGITS
    soever
    1.03
     you
    0.98
     intentional
    0.98
     they
    0.95
     consciously
    0.95
     it
    0.89
     intentionally
    0.87
     we
    0.79
     or
    0.74
     through
    0.71
    Activations Density 0.040%

    No Known Activations