© 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. 9962
    Prev
    Next
    INDEX
    Explanations

    words related to appreciation, support, and positivity

    oai_token-act-pair · gpt-3.5-turbo

    positive attributes and expressions of gratitude

    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
    toggle
    -0.73
     guiActiveUn
    -0.68
    edit
    -0.68
     dod
    -0.67
    aded
    -0.65
    udo
    -0.62
     Presumably
    -0.62
     Worse
    -0.62
    rez
    -0.62
    fix
    -0.61
    POSITIVE LOGITS
     compassionate
    0.81
     courageous
    0.78
     sacrific
    0.78
     philanthrop
    0.76
     stewards
    0.73
     multicultural
    0.73
     respectfully
    0.72
     comr
    0.72
     empowering
    0.71
     endeavors
    0.71
    Activations Density 1.783%

    No Known Activations