© 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. 8-RES-JB
    11. 3895
    Prev
    Next
    INDEX
    Explanations

    words related to positive moral qualities or ethical concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to moral or ethical goodness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eters
    -0.77
    ĸļ
    -0.76
    oths
    -0.73
    ptin
    -0.72
    ategory
    -0.71
    otta
    -0.70
    opers
    -0.70
    pper
    -0.68
     Sturgeon
    -0.67
    kson
    -0.67
    POSITIVE LOGITS
     intentions
    1.14
     Samar
    1.11
     deeds
    1.07
    reads
    1.07
     deed
    1.06
    enough
    1.01
     luck
    1.00
    luck
    0.97
    bye
    0.94
     ol
    0.93
    Activations Density 0.074%

    No Known Activations