© 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 EvalsExportsAPI 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. 4618
    Prev
    Next
    INDEX
    Explanations

    instances of negative scrutiny or criticism

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating increased scrutiny or criticism

    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
     sake
    -0.68
     Begins
    -0.67
     cures
    -0.63
     Potion
    -0.62
     dwarves
    -0.62
     caves
    -0.60
     Meridian
    -0.58
     Journals
    -0.58
     apes
    -0.57
    ents
    -0.57
    POSITIVE LOGITS
     scrutiny
    1.21
    whel
    0.89
     criticism
    0.89
     suspicion
    0.87
     fire
    0.85
     pressure
    0.83
     attention
    0.83
     tremend
    0.82
     scanner
    0.82
     brunt
    0.81
    Activations Density 0.039%

    No Known Activations