© 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. 20489
    Prev
    Next
    INDEX
    Explanations

    contact information with various mentions of reaching out to individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to contact information and accessibility in a document

    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
     spectator
    -0.58
     mosaic
    -0.55
     mates
    -0.53
     goggles
    -0.50
     Grind
    -0.49
    unin
    -0.49
     mosa
    -0.49
     fung
    -0.48
     Travels
    -0.48
     palate
    -0.48
    POSITIVE LOGITS
    DAY
    0.65
    EV
    0.64
    INESS
    0.64
    JR
    0.63
    DM
    0.62
    itely
    0.61
    dt
    0.58
    EMA
    0.58
    ataka
    0.57
    deen
    0.57
    Activations Density 0.116%

    No Known Activations