© 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. 0-RES-JB
    11. 7801
    Prev
    Next
    INDEX
    Explanations

    phrases related to obligations or compelling actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal duties and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atur
    -0.68
     TOD
    -0.62
    old
    -0.62
     Crew
    -0.62
     Current
    -0.61
     UC
    -0.59
     UI
    -0.59
    var
    -0.58
     Mid
    -0.58
     Whit
    -0.58
    POSITIVE LOGITS
     compelled
    3.19
     obliged
    3.02
     obligated
    2.13
     forced
    1.57
     coerced
    1.50
     persuaded
    1.50
     inclined
    1.48
     prevented
    1.46
     tempted
    1.44
     compel
    1.42
    Activations Density 0.025%

    No Known Activations