© 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. 0-RES-JB
    11. 11422
    Prev
    Next
    INDEX
    Explanations

    verbs related to expressing emotions or frustrations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "venting" or expressing emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    magic
    -0.75
     Literary
    -0.69
     Harper
    -0.68
    Os
    -0.68
    =>
    -0.65
     Library
    -0.65
    ibraries
    -0.65
     Bullets
    -0.64
     Binary
    -0.64
     Bless
    -0.64
    POSITIVE LOGITS
     vent
    3.88
     Vent
    2.56
     vents
    2.55
     ventilation
    2.00
    vent
    1.45
     duct
    1.37
     respir
    1.30
     dors
    1.10
     dorsal
    1.09
     valve
    0.99
    Activations Density 0.037%

    No Known Activations