© 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. 8-RES-JB
    11. 3177
    Prev
    Next
    INDEX
    Explanations

    phrases related to imposing rules, regulations, taxes, or sanctions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to imposition of laws and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.77
     Emin
    -0.77
    ickr
    -0.75
    ource
    -0.70
    ymph
    -0.69
    pring
    -0.65
    imble
    -0.62
    ucker
    -0.62
     Souls
    -0.62
    Untitled
    -0.61
    POSITIVE LOGITS
     restrictions
    1.21
     stricter
    1.18
     curfew
    1.17
     punishments
    1.11
     tariffs
    1.10
     penalties
    1.08
     strict
    1.06
     prohibitions
    1.06
     quotas
    1.04
     compulsory
    1.03
    Activations Density 0.268%

    No Known Activations