© 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. 5090
    Prev
    Next
    INDEX
    Explanations

    terms related to specific policy proposals or ideas in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to taxation and legislative reforms

    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
    minist
    -0.74
    APTER
    -0.67
    ournals
    -0.62
    hester
    -0.61
    resy
    -0.61
    Liberal
    -0.61
    ciplinary
    -0.60
    orem
    -0.59
    ollar
    -0.59
    iott
    -0.59
    POSITIVE LOGITS
     dancers
    0.64
    )</
    0.63
     chore
    0.62
     skating
    0.60
    netflix
    0.58
     toddlers
    0.57
     è£ıè
    0.57
     nod
    0.57
     rappers
    0.57
     dance
    0.56
    Activations Density 0.987%

    No Known Activations