© 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. 3295
    Prev
    Next
    INDEX
    Explanations

    instances of actions or events happening

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of actions and interactions involving characters in narratives

    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
    conservancy
    -0.68
    unless
    -0.64
    uably
    -0.62
    ©¶æ¥µ
    -0.61
    fleet
    -0.61
    avid
    -0.60
     Historically
    -0.60
    absolutely
    -0.59
    ãĥIJ
    -0.58
    ribe
    -0.58
    POSITIVE LOGITS
     finished
    0.95
     completion
    0.85
     completes
    0.81
    ward
    0.79
     arrival
    0.74
     expiration
    0.73
     arrives
    0.73
     returned
    0.70
     completed
    0.70
     expires
    0.70
    Activations Density 0.348%

    No Known Activations