© 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. 0-RES-JB
    6. 7783
    Prev
    Next
    INDEX
    Explanations

    strings related to medical terms, particularly focusing on bodily functions and specific names

    oai_token-act-pair · gpt-3.5-turbo

    specific chemical compounds or substances related to coatings or protective materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dele
    -0.75
     passport
    -0.75
     Photograph
    -0.74
     ident
    -0.69
     Fernand
    -0.68
     swat
    -0.68
     Ukip
    -0.67
     CCTV
    -0.67
     passports
    -0.66
     Advertisement
    -0.66
    POSITIVE LOGITS
    reth
    2.58
    rigan
    1.64
    bett
    1.37
    agues
    1.35
    lamm
    1.26
    areth
    1.18
    roth
    1.13
    NPR
    1.13
    pperc
    1.11
    ighty
    1.07
    Activations Density 0.066%

    No Known Activations