© 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. 3872
    Prev
    Next
    INDEX
    Explanations

    instances where specific numerical targets or goals are mentioned

    oai_token-act-pair · gpt-3.5-turbo

    goals or targets related to emissions and energy

    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
    Strange
    -0.71
    NetMessage
    -0.71
    inventoryQuantity
    -0.65
    ippi
    -0.63
     intrig
    -0.63
    inarily
    -0.63
    KNOWN
    -0.61
     puzzled
    -0.61
    quickShipAvailable
    -0.60
    wrong
    -0.59
    POSITIVE LOGITS
     5000
    1.07
     50
    1.05
     2020
    1.04
     6000
    1.04
     750
    1.04
     250
    1.02
     80
    1.02
     75
    1.01
     500
    1.01
     2025
    1.01
    Activations Density 0.339%

    No Known Activations