© 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. 6-RES-JB
    11. 14729
    Prev
    Next
    INDEX
    Explanations

    medical terms and drug-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to celebrities, particularly in a context of potential substance use or influence

    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
    ream
    -0.63
     immensely
    -0.60
    jab
    -0.55
     enormously
    -0.55
     Aval
    -0.55
     Rollins
    -0.54
     Hung
    -0.54
     Kavanaugh
    -0.54
     Marxist
    -0.53
     Shelley
    -0.53
    POSITIVE LOGITS
     thereof
    1.20
    depending
    1.12
     whichever
    0.90
     depending
    0.90
     versa
    0.82
    )?
    0.79
     altogether
    0.78
    itaire
    0.77
    abouts
    0.75
    Either
    0.74
    Activations Density 0.854%

    No Known Activations