© 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. 11-RES-JB
    11. 12482
    Prev
    Next
    INDEX
    Explanations

    adjectives and phrases related to quantity

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing positive traits or significant entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ernels
    -0.93
    Frames
    -0.91
    ships
    -0.90
    events
    -0.88
    frames
    -0.87
    casts
    -0.86
    lees
    -0.85
    pees
    -0.84
    ologies
    -0.82
    acs
    -0.82
    POSITIVE LOGITS
     researcher
    1.05
     spokesperson
    1.05
     commenter
    1.04
     spokeswoman
    1.03
     spokesman
    1.02
     glance
    0.98
     disclaimer
    0.97
    ccording
    0.96
     historian
    0.96
     reviewer
    0.93
    Activations Density 0.255%

    No Known Activations