© 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. 9-RES-JB
    11. 17054
    Prev
    Next
    INDEX
    Explanations

    sentences that start with "This"

    oai_token-act-pair · gpt-3.5-turbo

    markers or indicators of article structure and separation, particularly the placeholder for content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onto
    -0.83
    units
    -0.73
    aires
    -0.69
    KNOWN
    -0.68
    ickets
    -0.68
    pots
    -0.67
    iations
    -0.67
    ials
    -0.66
    nets
    -0.66
    arson
    -0.65
    POSITIVE LOGITS
     week
    1.07
     article
    1.04
     slideshow
    1.03
     morning
    0.90
     month
    0.88
     weekend
    0.88
     Week
    0.87
     concludes
    0.87
     infographic
    0.86
     column
    0.84
    Activations Density 0.134%

    No Known Activations