© 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. 9-RES-JB
    11. 15926
    Prev
    Next
    INDEX
    Explanations

    words related to positive attributes or actions, specifically focusing on "good"

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "good."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.76
    olate
    -0.76
    eteria
    -0.73
    lets
    -0.69
    kson
    -0.68
     Sturgeon
    -0.67
    eters
    -0.67
    apse
    -0.66
    otom
    -0.66
    ulous
    -0.65
    POSITIVE LOGITS
     intentions
    1.26
     deeds
    1.19
     deed
    1.14
     Samar
    1.10
     ol
    1.05
     luck
    1.00
    reads
    1.00
     manners
    0.95
     fortune
    0.93
    die
    0.93
    Activations Density 0.084%

    No Known Activations