© 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. 2622
    Prev
    Next
    INDEX
    Explanations

    words related to safety protocols and procedures

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, particularly "and" and "or", often used to connect related concepts or items

    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
    eda
    -0.77
     Tears
    -0.74
     Cyrus
    -0.70
     Advice
    -0.69
     Cohn
    -0.68
    oldemort
    -0.68
    PsyNetMessage
    -0.67
     Shiva
    -0.65
     Schumer
    -0.64
    $$$$
    -0.64
    POSITIVE LOGITS
    rogens
    1.17
    rogen
    1.12
    ifice
    0.96
     nons
    0.94
    chard
    0.87
    nam
    0.84
     outgoing
    0.83
    organic
    0.82
     nont
    0.82
     unarmed
    0.82
    Activations Density 0.164%

    No Known Activations