© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14882
    Prev
    Next
    INDEX
    Explanations

    Phrases related to legal and ethical considerations surrounding medical and social issues

    oai_token-act-pair · gpt-3.5-turbo

    sentences focused on specific subjects or actions related to responsibility and awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Europe
    -0.73
     Markus
    -0.71
    arts
    -0.70
    Alert
    -0.69
    oute
    -0.69
    Brexit
    -0.67
    Zen
    -0.67
     Raphael
    -0.67
     Fallon
    -0.66
     Rahman
    -0.65
    POSITIVE LOGITS
     person
    1.58
     recipient
    1.54
     perpetrator
    1.51
     offender
    1.44
     wearer
    1.36
     applicant
    1.34
     attacker
    1.32
     abuser
    1.31
     offending
    1.30
     claimant
    1.27
    Activations Density 0.332%

    No Known Activations