© 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. 4-RES-JB
    11. 15640
    Prev
    Next
    INDEX
    Explanations

    phrases related to childbirth and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "ce" likely in relation to medical or scientific contexts

    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
    STER
    -0.77
    DERR
    -0.76
     Skydragon
    -0.70
    stadt
    -0.70
    ested
    -0.68
     Kenobi
    -0.66
    izational
    -0.64
    ounces
    -0.63
    unci
    -0.63
    involved
    -0.63
    POSITIVE LOGITS
    utical
    1.03
    ce
    1.00
    les
    0.92
    rette
    0.87
    pter
    0.87
    re
    0.78
    llan
    0.76
    ipher
    0.74
    vez
    0.74
    ased
    0.73
    Activations Density 0.016%

    No Known Activations