© 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. 9-RES-JB
    11. 15925
    Prev
    Next
    INDEX
    Explanations

    phrases related to getting away with something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to getting away with actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arta
    -0.87
    wang
    -0.82
    atform
    -0.79
    ural
    -0.74
    agues
    -0.72
    stem
    -0.72
    ready
    -0.71
    wake
    -0.69
    sonian
    -0.68
     Ahead
    -0.68
    POSITIVE LOGITS
     murder
    1.05
     murdering
    0.96
     mischief
    0.91
     manslaughter
    0.90
     immoral
    0.89
     careless
    0.87
     reckless
    0.86
     anything
    0.86
     impunity
    0.85
     exploiting
    0.85
    Activations Density 0.081%

    No Known Activations