© 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. 11-RES-JB
    11. 15037
    Prev
    Next
    INDEX
    Explanations

    instances of the word "eff" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "effort."

    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
    meal
    -0.70
     oath
    -0.69
    ²¾
    -0.65
     Spur
    -0.64
     shortened
    -0.64
    SHIP
    -0.63
    Downloadha
    -0.63
    BOOK
    -0.62
    ciating
    -0.61
     uninterrupted
    -0.61
    POSITIVE LOGITS
    orts
    1.50
    luent
    1.44
    erves
    1.34
    endi
    1.25
    emin
    1.23
    usive
    1.20
    lore
    1.19
    ort
    1.16
    iency
    1.16
    usion
    1.15
    Activations Density 0.035%

    No Known Activations