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. 9340
    Prev
    Next
    INDEX
    Explanations

    words related to reducing or deductions

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "reduce."

    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
     custody
    -0.75
     SAM
    -0.68
     appointed
    -0.65
     Shaman
    -0.64
     Rahman
    -0.62
     Salman
    -0.62
     issued
    -0.61
     syn
    -0.60
     categor
    -0.59
    steps
    -0.57
    POSITIVE LOGITS
    uce
    4.65
    uces
    3.53
    uced
    3.37
    uction
    2.85
    ucing
    2.82
    ucer
    2.24
    uctions
    2.13
    uctive
    1.88
    uc
    1.43
    irect
    1.18
    Activations Density 0.018%

    No Known Activations