© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9560
    Prev
    Next
    INDEX
    Explanations

    terms related to mental health issues, such as 'lunatic' and variations including 'lunacy'

    oai_token-act-pair · gpt-3.5-turbo

    references to "lunacy" or "lunatics."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LECT
    -0.75
     Norn
    -0.69
     Proced
    -0.67
    USE
    -0.67
    Constructed
    -0.65
    âĢ¢âĢ¢
    -0.65
    ORN
    -0.64
    åĬ
    -0.63
    ORD
    -0.63
     Sorceress
    -0.62
    POSITIVE LOGITS
    cheon
    1.34
    acy
    1.26
    acies
    1.26
    atic
    1.23
    atics
    1.20
    atical
    1.08
    acists
    1.05
    aris
    0.98
    atos
    0.97
    aries
    0.97
    Activations Density 0.021%

    No Known Activations