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. 21247
    Prev
    Next
    INDEX
    Explanations

    specific times and numbers in a given text

    oai_token-act-pair · gpt-3.5-turbo

    specific time references or timestamps

    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
    ctors
    -0.62
    alog
    -0.59
     delegation
    -0.58
    ovych
    -0.55
     Lank
    -0.54
    itionally
    -0.54
     pipeline
    -0.53
    ority
    -0.53
     insulation
    -0.53
    iland
    -0.53
    POSITIVE LOGITS
     apiece
    1.02
     behest
    0.91
    point
    0.86
    mph
    0.80
    noon
    0.79
    mast
    0.78
     expense
    0.76
     glance
    0.74
     intersections
    0.74
     speeds
    0.73
    Activations Density 0.119%

    No Known Activations