© 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. 6-RES-JB
    11. 18429
    Prev
    Next
    INDEX
    Explanations

    references to voluntary actions or agreements

    oai_token-act-pair · gpt-3.5-turbo

    references to voluntary actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    marks
    -0.79
     Tycoon
    -0.78
    mers
    -0.78
    sworth
    -0.78
    alon
    -0.73
    abal
    -0.73
    osite
    -0.73
    efully
    -0.72
    raph
    -0.72
    geist
    -0.71
    POSITIVE LOGITS
    untarily
    1.08
    untary
    1.04
     manslaughter
    1.01
     voluntary
    0.95
     surrender
    0.95
    unte
    0.93
     relinqu
    0.88
     involuntary
    0.85
     enlist
    0.82
     euth
    0.80
    Activations Density 0.021%

    No Known Activations