© 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. 10399
    Prev
    Next
    INDEX
    Explanations

    commands to consider something or pay attention to something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that encourage the reader to take action or look at specific information

    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
     advertised
    -0.66
     constitu
    -0.65
    tions
    -0.63
     accompanies
    -0.62
    ambo
    -0.61
    ansas
    -0.59
     wart
    -0.59
     dissatisf
    -0.56
    idding
    -0.56
    Develop
    -0.56
    POSITIVE LOGITS
    aways
    1.31
     advantage
    1.19
     heed
    1.09
    away
    1.02
     aback
    0.98
     away
    0.91
     care
    0.90
     precautions
    0.86
     liberties
    0.86
     Advantage
    0.84
    Activations Density 0.069%

    No Known Activations