© 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. 9-RES-JB
    11. 11184
    Prev
    Next
    INDEX
    Explanations

    phrases related to pondering or considering a specific situation or question

    oai_token-act-pair · gpt-3.5-turbo

    phrases that pose rhetorical questions, particularly starting with "you know what."

    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
    ãģ®éŃĶ
    -0.81
    gem
    -0.69
    yrinth
    -0.64
    draft
    -0.63
    Weiss
    -0.62
    estone
    -0.62
    trak
    -0.61
    cul
    -0.61
    gur
    -0.60
    hips
    -0.60
    POSITIVE LOGITS
     happens
    1.29
     happened
    1.23
     happ
    1.16
     else
    1.08
     ensued
    0.92
    ?!
    0.77
     kinda
    0.76
    !?
    0.75
     transpired
    0.75
    ?
    0.74
    Activations Density 0.046%

    No Known Activations