© 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. 7-RES-JB
    11. 1543
    Prev
    Next
    INDEX
    Explanations

    terms related to societal issues, such as domestic violence, healthcare facilities, and accountability

    oai_token-act-pair · gpt-3.5-turbo

    topics related to health and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.51
    Ö¼
    -0.50
    ensional
    -0.50
     Democr
    -0.50
    pard
    -0.43
    noon
    -0.43
    minist
    -0.42
     sooner
    -0.42
    ffer
    -0.41
    Ö
    -0.41
    POSITIVE LOGITS
     etc
    1.14
    etc
    0.58
     thereof
    0.55
    !,
    0.51
     TBA
    0.50
    ,...
    0.50
    *,
    0.49
    +,
    0.49
     ect
    0.48
     &
    0.47
    Activations Density 0.744%

    No Known Activations