© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 20335
    Prev
    Next
    INDEX
    Explanations

    concepts related to finance and economics

    oai_token-act-pair · gpt-3.5-turbo

    critical terms related to finance, health, and societal structures

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

    No Comments

    Negative Logits
    erker
    -0.60
    awaru
    -0.56
    ixties
    -0.55
    Ö¼
    -0.52
     Edmund
    -0.50
     Heller
    -0.49
    oneliness
    -0.49
     partName
    -0.48
     Gle
    -0.48
     Thur
    -0.48
    POSITIVE LOGITS
     securely
    0.60
    onto
    0.58
     ASAP
    0.58
    grade
    0.57
    fml
    0.56
    bucks
    0.56
    license
    0.56
    oops
    0.54
     someday
    0.54
     tomorrow
    0.54
    Activations Density 1.511%

    No Known Activations