© 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. 15463
    Prev
    Next
    INDEX
    Explanations

    Latin terms or names, specifically those with the prefix "Est."

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific statistical terms or metrics

    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
     ribs
    -0.67
     worms
    -0.64
    sheets
    -0.61
    legged
    -0.61
     snakes
    -0.61
     dwarves
    -0.60
     nipples
    -0.60
     steroids
    -0.60
     feathers
    -0.59
     dracon
    -0.59
    POSITIVE LOGITS
     Lauder
    0.98
    ement
    0.93
    itures
    0.92
    ciating
    0.89
    ateg
    0.87
    ements
    0.84
    enza
    0.84
    acion
    0.84
    ADRA
    0.83
    ondo
    0.82
    Activations Density 0.104%

    No Known Activations