© 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. 5368
    Prev
    Next
    INDEX
    Explanations

    adjectives describing moral or ethical characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey moral or philosophical judgments

    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
    ãģ®éŃĶ
    -0.80
    ciation
    -0.79
    engine
    -0.78
    icular
    -0.76
    ires
    -0.74
    ecycle
    -0.73
    INAL
    -0.71
    eor
    -0.71
    redits
    -0.70
    aneous
    -0.69
    POSITIVE LOGITS
     seeing
    1.46
     knowing
    1.42
     having
    1.41
     pretending
    1.32
     owning
    1.30
     witnessing
    1.28
     watching
    1.28
     letting
    1.27
     imagining
    1.25
     admitting
    1.23
    Activations Density 0.268%

    No Known Activations