© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 4941
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to being part of a series, sequel, or a sequence

    oai_token-act-pair · gpt-3.5-turbo

    references to sequences or installments in a series

    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
    bos
    -0.72
    entimes
    -0.66
     interacted
    -0.64
    terday
    -0.62
    utterstock
    -0.62
    onday
    -0.61
     nevertheless
    -0.60
     palms
    -0.60
     volunteered
    -0.58
     vulner
    -0.58
    POSITIVE LOGITS
     series
    1.00
    series
    0.90
     Series
    0.88
     trilogy
    0.85
     succession
    0.81
     Line
    0.77
     line
    0.76
    Series
    0.74
     LINE
    0.74
     Branch
    0.65
    Activations Density 0.151%

    No Known Activations