© 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. 10-RES-JB
    11. 2260
    Prev
    Next
    INDEX
    Explanations

    words related to biological and medical sciences, particularly focusing on the "os" suffix that often relates to bone formation or medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the field of psychology and its scientific principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jehovah
    -0.66
     Slov
    -0.66
    LESS
    -0.65
    ãĤ¡
    -0.63
     Fool
    -0.62
     Jesus
    -0.61
     Rom
    -0.61
     Madonna
    -0.58
     Sparkle
    -0.58
     Nightmares
    -0.58
    POSITIVE LOGITS
    ocial
    1.55
    keleton
    1.52
    atellite
    1.48
    ystem
    1.47
    cience
    1.43
    omal
    1.40
    clerosis
    1.34
    omes
    1.29
    pora
    1.29
    oci
    1.27
    Activations Density 0.048%

    No Known Activations