© 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. 8-RES-JB
    11. 11358
    Prev
    Next
    INDEX
    Explanations

    terms related to completion or entirety

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "full" in various contexts

    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
    lees
    -0.99
    groups
    -0.93
    hops
    -0.89
    items
    -0.87
    stories
    -0.87
    sites
    -0.86
    events
    -0.84
    aunts
    -0.84
    forts
    -0.82
    units
    -0.80
    POSITIVE LOGITS
     explanation
    1.02
     indication
    1.01
     apology
    0.99
     breakdown
    0.97
     dose
    0.97
     halt
    0.95
     glimpse
    0.94
     solution
    0.93
     demonstration
    0.92
     overhaul
    0.92
    Activations Density 0.263%

    No Known Activations