© 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. 17487
    Prev
    Next
    INDEX
    Explanations

    words related to non-lethal tools and objects

    oai_token-act-pair · gpt-3.5-turbo

    negations and qualifiers related to safety and compliance in various contexts

    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
     leadership
    -0.84
     negotiations
    -0.84
     entitlement
    -0.82
     professions
    -0.78
     achievements
    -0.76
     keynote
    -0.76
     acknowled
    -0.74
     preferences
    -0.74
     sentiments
    -0.74
     Events
    -0.74
    POSITIVE LOGITS
    mounted
    1.23
    colored
    1.21
    assembled
    1.14
    printed
    1.14
    fitted
    1.12
    painted
    1.11
    usable
    1.09
    worn
    1.09
    shaped
    1.07
    uminum
    1.05
    Activations Density 0.242%

    No Known Activations