© 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. 6-RES-JB
    11. 14686
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or financial loopholes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal loopholes and their exploitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    semble
    -0.64
    itatively
    -0.62
    arya
    -0.61
    olute
    -0.60
     Archangel
    -0.60
    ointed
    -0.59
    oran
    -0.59
    itate
    -0.59
    grave
    -0.58
    sis
    -0.58
    POSITIVE LOGITS
     loopholes
    1.25
     loophole
    1.12
    glers
    1.05
    door
    0.95
     exemptions
    0.88
     amnesty
    0.81
    vernment
    0.78
     circumvent
    0.74
    back
    0.74
    behind
    0.74
    Activations Density 0.027%

    No Known Activations