© 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. 5413
    Prev
    Next
    INDEX
    Explanations

    comparative statements using the structure "What's more" to emphasize additional information or points

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "what's more," indicating additional information or a point of emphasis

    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
    oided
    -0.72
    psc
    -0.68
    phia
    -0.68
    sha
    -0.65
     actionGroup
    -0.64
    assetsadobe
    -0.64
    osures
    -0.59
    mates
    -0.59
    ãĥĥãĥī
    -0.58
    izon
    -0.58
    POSITIVE LOGITS
     worrisome
    1.14
     surprising
    1.12
     interesting
    1.12
     important
    1.11
     troubling
    1.11
     alarming
    1.09
     intriguing
    1.08
     astounding
    1.07
     disturbing
    1.06
     impressive
    1.06
    Activations Density 0.031%

    No Known Activations