© 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. 4995
    Prev
    Next
    INDEX
    Explanations

    references to different types of entities such as species, objects, professions, and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of animals and various community-related entities

    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
    ishment
    -0.73
     guiName
    -0.64
     Nightmare
    -0.63
    ONSORED
    -0.63
    iday
    -0.62
    KEN
    -0.62
    enance
    -0.62
    IER
    -0.61
    tesy
    -0.61
     Kane
    -0.61
    POSITIVE LOGITS
    etc
    1.37
     etc
    1.28
     Flavoring
    0.89
     assorted
    0.80
    whatever
    0.75
     carbohyd
    0.74
     routers
    0.70
     alike
    0.68
     carriers
    0.68
    âĢ¦)
    0.68
    Activations Density 0.251%

    No Known Activations