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

    Neuronpedia

    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. 8-RES-JB
    11. 2519
    Prev
    Next
    INDEX
    Explanations

    words related to government, regulations, and processes

    oai_token-act-pair · gpt-3.5-turbo

    variations of the root word relating to "trans" and "gen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wol
    -0.75
     Cot
    -0.72
     Shepherd
    -0.71
     Immunity
    -0.69
     Worlds
    -0.69
     Tone
    -0.69
     Decker
    -0.68
     BMC
    -0.67
     Painter
    -0.66
     Bulg
    -0.66
    POSITIVE LOGITS
    amental
    1.12
    secut
    1.09
    anced
    1.08
    acters
    1.07
    estial
    1.05
    estic
    1.05
    ature
    1.04
    ipment
    1.03
    inent
    1.03
    oved
    1.02
    Activations Density 0.193%

    No Known Activations