© 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. 3541
    Prev
    Next
    INDEX
    Explanations

    phrases indicating apologies or regret

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to apologies and advocates

    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
     Jiu
    -0.80
     Vader
    -0.74
     MID
    -0.70
     Peb
    -0.68
     Tunis
    -0.65
    enegger
    -0.65
     Dortmund
    -0.64
     Karn
    -0.64
     passer
    -0.64
     Ceres
    -0.63
    POSITIVE LOGITS
    acy
    1.52
    etics
    1.42
    etic
    1.41
    ates
    1.35
    etically
    1.23
    acists
    1.18
    acies
    1.15
    otes
    1.12
    ats
    1.03
    acist
    1.02
    Activations Density 0.071%

    No Known Activations