© 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. 21218
    Prev
    Next
    INDEX
    Explanations

    verbs related to reacting or responding strongly

    oai_token-act-pair · gpt-3.5-turbo

    instances of people expressing strong negative reactions or criticism

    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
     optimum
    -0.67
    ////////////////////////////////
    -0.65
     equals
    -0.65
     Transactions
    -0.63
     americ
    -0.63
     perfected
    -0.62
     surplus
    -0.62
     ILCS
    -0.59
    fuck
    -0.58
     conceal
    -0.56
    POSITIVE LOGITS
     angrily
    1.14
     harshly
    1.10
     sharply
    1.09
     forcefully
    1.05
     strongly
    1.04
     vehemently
    1.02
     furiously
    0.99
    Wednesday
    0.94
     Wednesday
    0.91
     sarcast
    0.90
    Activations Density 0.126%

    No Known Activations