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. 23877
    Prev
    Next
    INDEX
    Explanations

    words related to a specific proper noun or name, "Zy."

    oai_token-act-pair · gpt-3.5-turbo

    words that suggest a casual or relaxed attitude

    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
     contr
    -0.80
     contrary
    -0.72
     Govern
    -0.65
     sea
    -0.64
     medium
    -0.63
     Mull
    -0.62
     stocks
    -0.61
     fault
    -0.61
     Concord
    -0.60
     Coil
    -0.59
    POSITIVE LOGITS
    zy
    4.66
    zes
    2.01
    zed
    1.94
    ze
    1.82
    zie
    1.71
    zer
    1.65
    zing
    1.57
    zn
    1.51
    zyk
    1.50
    zen
    1.46
    Activations Density 0.009%

    No Known Activations