© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2974
    Prev
    Next
    INDEX
    Explanations

    terms related to ethics or ethical considerations

    oai_token-act-pair · gpt-3.5-turbo

    references to ethical issues and considerations, particularly regarding animals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Vaj
    -0.79
     Sakura
    -0.68
     Courier
    -0.66
     clearing
    -0.65
     Colleg
    -0.64
     Breach
    -0.63
     Leap
    -0.63
     Cain
    -0.63
     Holmes
    -0.62
     Wass
    -0.62
    POSITIVE LOGITS
    ically
    1.49
    ical
    1.47
    icist
    1.41
    ics
    1.38
    ylene
    1.37
    ological
    1.32
    ologically
    1.25
    nom
    1.23
    iop
    1.21
    onym
    1.20
    Activations Density 0.030%

    No Known Activations