© 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. 9-RES-JB
    11. 11150
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the quality or desirability of items

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that express quality or desirability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lees
    -0.93
    ometers
    -0.88
    steps
    -0.88
    ernels
    -0.86
    aucuses
    -0.84
    hops
    -0.82
    tests
    -0.79
    ships
    -0.79
    levels
    -0.78
    events
    -0.78
    POSITIVE LOGITS
     piece
    1.21
     chunk
    1.07
     person
    0.99
     sized
    0.98
     paycheck
    0.98
     dose
    0.96
     meal
    0.96
     pair
    0.94
     slice
    0.92
     adversary
    0.91
    Activations Density 0.403%

    No Known Activations