© 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. 2757
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "relatively."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "relatively" and its variations

    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
    andel
    -0.66
    igan
    -0.64
     Iris
    -0.62
     Seasons
    -0.62
    osis
    -0.61
    ved
    -0.61
    ournals
    -0.60
    igon
    -0.60
    Ö¼
    -0.60
    ULTS
    -0.59
    POSITIVE LOGITS
     innocuous
    1.11
     inexpensive
    1.11
     benign
    1.11
     harmless
    1.10
     tame
    1.10
     unpop
    1.05
     insignificant
    1.04
     straightforward
    1.00
     unaffected
    0.96
     uncont
    0.95
    Activations Density 0.047%

    No Known Activations