© 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. 11-RES-JB
    11. 7644
    Prev
    Next
    INDEX
    Explanations

    URLs and tracking parameters within text

    oai_token-act-pair · gpt-3.5-turbo

    query parameters and structured data in URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flawless
    -0.70
     crochet
    -0.69
     Gron
    -0.69
     Dancing
    -0.68
     Drift
    -0.68
     orche
    -0.67
     Cascade
    -0.66
     Cry
    -0.63
     smoother
    -0.63
    issance
    -0.63
    POSITIVE LOGITS
    utm
    1.53
    hl
    1.25
    lang
    1.25
    context
    1.23
    src
    1.21
    pid
    1.21
    sid
    1.20
    uid
    1.15
    tag
    1.12
    page
    1.11
    Activations Density 0.036%

    No Known Activations