© 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. 20929
    Prev
    Next
    INDEX
    Explanations

    references to personal growth and self-improvement

    oai_token-act-pair · gpt-3.5-turbo

    key phrases related to personal development and life lessons

    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
     disg
    -0.92
     princ
    -0.91
     convol
    -0.91
     conclud
    -0.89
     increment
    -0.89
     crest
    -0.88
     snowball
    -0.88
     dipping
    -0.88
     satell
    -0.87
     culminating
    -0.85
    POSITIVE LOGITS
     Them
    1.79
     Yourself
    1.73
     Your
    1.60
     Their
    1.59
     Different
    1.57
     About
    1.55
     Its
    1.52
     Everything
    1.52
     Someone
    1.49
     Possible
    1.48
    Activations Density 0.312%

    No Known Activations