© 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. 1-RES-JB
    11. 5034
    Prev
    Next
    INDEX
    Explanations

    words related to inappropriate or unacceptable behavior

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "uncertain" or its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    姫
    -0.92
    uyomi
    -0.91
     Solitaire
    -0.75
    =-=-=-=-
    -0.74
    heid
    -0.72
    =-=-=-=-=-=-=-=-
    -0.71
    MENT
    -0.71
     fronts
    -0.70
    Downloadha
    -0.70
    utenant
    -0.69
    POSITIVE LOGITS
    ursed
    0.99
    oded
    0.91
    ount
    0.89
    redited
    0.88
    reated
    0.87
    ooked
    0.87
     unc
    0.81
    aleb
    0.81
    icated
    0.81
    ashed
    0.80
    Activations Density 0.004%

    No Known Activations