© 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. 362
    Prev
    Next
    INDEX
    Explanations

    phrases related to engaging in activities or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "engaging in."

    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
    ario
    -0.73
    arily
    -0.71
    lights
    -0.70
    mother
    -0.70
    ended
    -0.69
    orah
    -0.69
    ãĥ¼ãĥ³
    -0.69
    esa
    -0.68
    installed
    -0.67
     ported
    -0.67
    POSITIVE LOGITS
     conversation
    0.97
     vigorous
    0.96
     meaningful
    0.93
     hostilities
    0.89
     dialogue
    0.88
     risky
    0.87
     reckless
    0.86
     conversations
    0.85
     mutual
    0.85
     continual
    0.84
    Activations Density 0.104%

    No Known Activations