© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6-RES-JB
    11. 17200
    Prev
    Next
    INDEX
    Explanations

    phrases indicating coercion or forceful actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of being compelled or forced to take specific actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laughter
    -0.72
     Compass
    -0.66
     Blueprint
    -0.66
    icious
    -0.65
     Prediction
    -0.65
     Garland
    -0.64
    cli
    -0.63
     Messages
    -0.63
    calling
    -0.63
    ergy
    -0.61
    POSITIVE LOGITS
     endure
    1.09
     confront
    1.01
     reckon
    1.00
     rethink
    0.96
     fend
    0.93
     reconsider
    0.92
     flee
    0.87
     cancel
    0.87
     abandon
    0.86
     undertake
    0.84
    Activations Density 0.068%

    No Known Activations