© 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. 6-RES-JB
    11. 5032
    Prev
    Next
    INDEX
    Explanations

    phrases related to accepting or rejecting offers or statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating acceptance or an invitation

    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
    abouts
    -0.71
    ixt
    -0.70
    encia
    -0.68
     Alley
    -0.68
    mAh
    -0.68
    lette
    -0.66
    yip
    -0.66
    ginx
    -0.65
    ibaba
    -0.65
    edin
    -0.65
    POSITIVE LOGITS
     invitation
    0.91
     premise
    0.84
     uncond
    0.79
     unres
    0.76
     gladly
    0.72
     advances
    0.69
     responsibility
    0.69
     validity
    0.68
     tentative
    0.67
     grate
    0.66
    Activations Density 0.173%

    No Known Activations