© 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 EvalsExportsAPI 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. 10-RES-JB
    11. 4885
    Prev
    Next
    INDEX
    Explanations

    references to well-being and quality of life

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ¥µ
    -0.75
    omore
    -0.74
    itton
    -0.72
    rely
    -0.72
    ategory
    -0.71
    cffff
    -0.64
    ongyang
    -0.64
    irlf
    -0.62
    committee
    -0.61
    ules
    -0.58
    POSITIVE LOGITS
    spring
    1.26
    esley
    1.01
    -
    1.01
     behaved
    0.93
    iberal
    0.91
    âĢIJ
    0.89
    known
    0.88
    Known
    0.86
    rounded
    0.86
     deserved
    0.83
    Activations Density 0.033%

    No Known Activations