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. 10-RES-JB
    6. 20980
    Prev
    Next
    INDEX
    Explanations

    copyright notices with associated years

    oai_token-act-pair · gpt-3.5-turbo

    copyright information and dates of publication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     upside
    -0.80
     setting
    -0.66
    ment
    -0.63
    viation
    -0.61
    ¸
    -0.61
    asking
    -0.59
    gettable
    -0.59
     pockets
    -0.59
     queue
    -0.58
     nearest
    -0.58
    POSITIVE LOGITS
     Globe
    0.95
    20439
    0.87
     Creat
    0.80
     Tribune
    0.80
     Intellectual
    0.79
     Nex
    0.76
     Associated
    0.75
     IEEE
    0.75
     Spectrum
    0.73
     NPR
    0.73
    Activations Density 0.018%

    No Known Activations