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

    Neuronpedia

    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. 0-RES-JB
    11. 18115
    Prev
    Next
    INDEX
    Explanations

    sections related to additional information or items in a text

    oai_token-act-pair · gpt-3.5-turbo

    the term "Additional" and associated annotations or labels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stupid
    -0.82
     politic
    -0.73
     boring
    -0.71
     real
    -0.69
     win
    -0.69
     flip
    -0.69
     sane
    -0.68
     humour
    -0.67
     lately
    -0.66
     shake
    -0.65
    POSITIVE LOGITS
     Additional
    3.10
    Additional
    3.05
     Extra
    1.34
     Optional
    1.30
    Extra
    1.28
     additional
    1.12
    Further
    1.10
     Approximately
    1.08
     Supplementary
    1.07
    Special
    1.07
    Activations Density 0.018%

    No Known Activations