© 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. 5404
    Prev
    Next
    INDEX
    Explanations

    the phrase "there is not much" or similar instances where the concept of a lack of quantity is described

    oai_token-act-pair · gpt-3.5-turbo

    expressions of scarcity or lack

    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
    utenberg
    -0.75
    idem
    -0.68
    PHOTOS
    -0.68
    cessive
    -0.65
    htaking
    -0.64
    olkien
    -0.63
    hani
    -0.63
    esm
    -0.62
    fters
    -0.62
     incorrectly
    -0.61
    POSITIVE LOGITS
     left
    1.27
     recourse
    1.16
     anymore
    1.10
     remaining
    1.08
     viable
    1.01
     hope
    0.98
     salvage
    0.92
     stopping
    0.86
     surviving
    0.85
    chance
    0.82
    Activations Density 0.371%

    No Known Activations