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. 8-RES-JB
    6. 16320
    Prev
    Next
    INDEX
    Explanations

    sentences with a call to action

    oai_token-act-pair · gpt-3.5-turbo

    discussions about lists or rankings of various topics or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     externalToEVAOnly
    -0.84
    ebus
    -0.71
     initi
    -0.70
    xit
    -0.67
     renegoti
    -0.67
    engers
    -0.67
     withdrawing
    -0.63
    adan
    -0.62
    ocrin
    -0.61
     diseng
    -0.60
    POSITIVE LOGITS
     curated
    1.07
     roundup
    1.04
     infographic
    1.03
     alphabet
    1.02
     list
    0.97
    ottest
    0.96
     favorites
    0.93
    Below
    0.89
     rundown
    0.87
     bookmark
    0.86
    Activations Density 0.626%

    No Known Activations