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. 8764
    Prev
    Next
    INDEX
    Explanations

    expressions related to missed opportunities or alternative scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the notion of opportunities lost or potential that was not realized

    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
     Deb
    -0.68
     currently
    -0.64
     presently
    -0.63
     now
    -0.63
     usually
    -0.62
    ftime
    -0.62
    adj
    -0.60
     Dj
    -0.59
    verend
    -0.58
     nightly
    -0.57
    POSITIVE LOGITS
     sooner
    0.87
    MpServer
    0.78
    anship
    0.70
    ?????-
    0.69
    Ire
    0.69
    ypes
    0.68
    wolves
    0.66
     unthinkable
    0.66
    Title
    0.66
    better
    0.64
    Activations Density 0.192%

    No Known Activations