© 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. 7-RES-JB
    11. 20912
    Prev
    Next
    INDEX
    Explanations

    mentions of legal consequences and disobedience towards authority

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal contempt and obstruction of justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nas
    -0.82
    makers
    -0.81
    ndra
    -0.80
    eor
    -0.80
    bourg
    -0.77
    erk
    -0.74
    tt
    -0.73
    llers
    -0.70
    kov
    -0.69
    maker
    -0.68
    POSITIVE LOGITS
    uously
    1.28
    uous
    1.24
    ible
    0.99
    ensibly
    0.84
    atural
    0.78
     unfocusedRange
    0.77
    uments
    0.76
    atus
    0.76
    igent
    0.76
    ciating
    0.75
    Activations Density 0.039%

    No Known Activations