© 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. 2-RES-JB
    11. 23799
    Prev
    Next
    INDEX
    Explanations

    mentions of names ending in "di" with varying levels of specificity and relevance to the text

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to the topic of diabetes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.80
    Reviewer
    -0.75
    INGS
    -0.67
     Spaces
    -0.67
     EVs
    -0.67
     suspense
    -0.66
    ï¸ı
    -0.64
    LESS
    -0.64
     Dangerous
    -0.64
    */(
    -0.64
    POSITIVE LOGITS
    plom
    1.30
    urnal
    1.23
    abetes
    1.23
    agonal
    1.19
    ploma
    1.18
    ablo
    1.11
    ocese
    1.08
    agram
    1.04
    ption
    1.02
    pling
    0.97
    Activations Density 0.007%

    No Known Activations