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. 0-RES-JB
    6. 959
    Prev
    Next
    INDEX
    Explanations

    phrases following the word "and"

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     visible
    -0.59
     circus
    -0.57
     sucked
    -0.56
     recipients
    -0.55
     reciproc
    -0.54
     lid
    -0.53
     complying
    -0.52
     detectable
    -0.52
     brush
    -0.52
     revolt
    -0.51
    POSITIVE LOGITS
    and
    3.57
    ands
    2.04
    AND
    1.89
    ande
    1.88
    andan
    1.77
    anded
    1.76
    anders
    1.75
    anding
    1.58
    along
    1.57
    andra
    1.52
    Activations Density 0.031%

    No Known Activations