© 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. 9583
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or businesses called "Regency"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific regulation or governing body

    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
    lihood
    -0.83
    hower
    -0.76
     Sense
    -0.71
    ¿½
    -0.70
     Dangerous
    -0.68
    ÙIJ
    -0.68
    WARE
    -0.66
    \\\\\\\\
    -0.66
    ï¸
    -0.64
    hyde
    -0.64
    POSITIVE LOGITS
    arded
    1.08
    inal
    1.05
    nant
    1.04
    rett
    1.03
    ulators
    1.02
    aining
    1.00
    ardless
    0.99
    rets
    0.98
    atta
    0.98
    olith
    0.98
    Activations Density 0.024%

    No Known Activations