© 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. 3-RES-JB
    11. 3222
    Prev
    Next
    INDEX
    Explanations

    phrases related to strict adherence or enforcement of rules, guidelines, or conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating strictness or adherence to rules

    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
    lain
    -0.84
     Tycoon
    -0.84
    ocene
    -0.72
    ilater
    -0.72
    Pokémon
    -0.69
     Healing
    -0.69
    ulton
    -0.68
    okemon
    -0.67
    igate
    -0.66
    assies
    -0.65
    POSITIVE LOGITS
     prohibited
    0.99
     minded
    0.94
     exempted
    0.92
     enforced
    0.87
    tics
    0.86
     exempt
    0.84
     adherent
    0.84
     speaking
    0.83
     adhere
    0.82
     obliged
    0.81
    Activations Density 0.004%

    No Known Activations