© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1427
    Prev
    Next
    INDEX
    Explanations

    phrases indicating setting out or embarking on a specific task or journey

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the initiation of actions or journeys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itu
    -0.67
    avorable
    -0.62
    aird
    -0.60
     closed
    -0.59
    colo
    -0.57
     elapsed
    -0.57
     Advantage
    -0.56
     transitioned
    -0.55
     outage
    -0.55
    ilege
    -0.55
    POSITIVE LOGITS
     anew
    0.98
     boldly
    0.86
    fitted
    0.83
     towards
    0.83
     toward
    0.79
     to
    0.75
    iscover
    0.74
    posts
    0.74
    tracking
    0.68
     intending
    0.68
    Activations Density 0.088%

    No Known Activations