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. 1-RES-JB
    6. 13729
    Prev
    Next
    INDEX
    Explanations

    noun form words related to the conception or creation of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of conception and the act of conceiving ideas or children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Universities
    -0.76
    cler
    -0.66
    anwhile
    -0.65
     footh
    -0.63
     outspoken
    -0.63
    upon
    -0.63
     piled
    -0.62
     whistle
    -0.61
     universities
    -0.61
     religions
    -0.61
    POSITIVE LOGITS
     conceived
    1.15
     conceive
    0.95
    actionDate
    0.90
    ceived
    0.84
    agram
    0.77
    smanship
    0.75
    ortion
    0.74
     ART
    0.74
     conception
    0.74
    \'
    0.72
    Activations Density 0.007%

    No Known Activations