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. 17641
    Prev
    Next
    INDEX
    Explanations

    sentences conveying a sense of tension or challenge

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "but" indicating contrast or complications in narratives

    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
    UD
    -0.73
    pron
    -0.72
    pec
    -0.72
    tnc
    -0.71
    NULL
    -0.67
    AMP
    -0.67
    usal
    -0.65
    actionDate
    -0.64
    igmat
    -0.63
    ungle
    -0.62
    POSITIVE LOGITS
     luckily
    1.52
     fortunately
    1.51
     nevertheless
    1.47
     nonetheless
    1.42
     thankfully
    1.27
     hey
    1.25
     mirac
    0.90
     otherwise
    0.88
     somehow
    0.87
     tolerated
    0.87
    Activations Density 0.216%

    No Known Activations