© 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. 11383
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives related to reducing or lowering something

    oai_token-act-pair · gpt-3.5-turbo

    comparative statements emphasizing decreased quantities or importance

    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
    Ds
    -0.71
    oÄŁ
    -0.68
    ULE
    -0.66
    Disclaimer
    -0.65
     Enhancement
    -0.64
    icion
    -0.63
     Advis
    -0.63
    WAYS
    -0.62
    å¯
    -0.60
    ixtures
    -0.60
    POSITIVE LOGITS
    ened
    1.31
     than
    1.25
    ening
    1.17
    ens
    0.90
     forgiving
    0.88
     inclined
    0.84
     glamorous
    0.84
     fortunate
    0.84
     traveled
    0.83
     intrusive
    0.78
    Activations Density 0.052%

    No Known Activations