© 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. 12374
    Prev
    Next
    INDEX
    Explanations

    conversations and emotional expressions

    oai_token-act-pair · gpt-3.5-turbo

    emotional expressions and reactions

    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
     credential
    -1.01
     freight
    -0.91
     nationally
    -0.81
     lockout
    -0.81
     prosec
    -0.81
     burglary
    -0.81
    mercial
    -0.81
     divest
    -0.80
     charter
    -0.79
     statewide
    -0.79
    POSITIVE LOGITS
    ãĢĮ
    1.48
    Anyway
    1.44
    Elsa
    1.33
    Alright
    1.29
    ãĥİ
    1.28
    Honestly
    1.28
    Yeah
    1.24
     Sakuya
    1.23
     ãĢĮ
    1.22
    Hmm
    1.22
    Activations Density 0.324%

    No Known Activations