© 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. 1-RES-JB
    11. 14223
    Prev
    Next
    INDEX
    Explanations

    references related to germination and medical terms related to geriatrics

    oai_token-act-pair · gpt-3.5-turbo

    words related to germs and germination processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quished
    -0.72
    lift
    -0.71
    aepernick
    -0.71
    HCR
    -0.70
    ollower
    -0.70
    ĸļ
    -0.69
    ivia
    -0.69
    awaru
    -0.69
    eeper
    -0.68
     compuls
    -0.68
    POSITIVE LOGITS
     ger
    1.43
     germ
    0.86
    fect
    0.86
     spores
    0.83
     indoors
    0.83
     Dise
    0.74
     Infect
    0.73
    bial
    0.73
     pathogens
    0.72
    apons
    0.72
    Activations Density 0.007%

    No Known Activations