© 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 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. 3-RES-JB
    11. 24002
    Prev
    Next
    INDEX
    Explanations

    phrases related to coercion

    oai_token-act-pair · gpt-3.5-turbo

    references to coercion and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izen
    -0.80
     Ion
    -0.78
    hop
    -0.72
    ARK
    -0.72
    arks
    -0.71
     Blessed
    -0.71
    gal
    -0.71
     Balanced
    -0.70
     Maintenance
    -0.70
     Anthem
    -0.69
    POSITIVE LOGITS
     coer
    1.14
     coerced
    1.12
     coercion
    0.99
     compel
    0.83
     coerc
    0.83
     pressuring
    0.82
     blackmail
    0.81
     pressured
    0.77
     coercive
    0.77
    ãĥį
    0.73
    Activations Density 0.016%

    No Known Activations