© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 13705
    Prev
    Next
    INDEX
    Explanations

    words related to extraordinary abilities and capabilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating capabilities or abilities

    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
    soDeliveryDate
    -0.87
    soType
    -0.64
    evidence
    -0.62
     largeDownload
    -0.61
    rant
    -0.61
     Zah
    -0.60
     thanking
    -0.60
     Commissioners
    -0.60
     Federation
    -0.60
    )=(
    -0.60
    POSITIVE LOGITS
     withstand
    1.40
     tolerate
    1.21
     handle
    1.16
     cope
    1.13
     survive
    1.13
     communicate
    1.12
     operate
    1.12
     endure
    1.11
     manipulate
    1.05
     perform
    1.05
    Activations Density 0.176%

    No Known Activations