© 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. 10-RES-JB
    11. 18760
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating degree or intensity

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers or adjectives that emphasize quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    culosis
    -0.78
    axter
    -0.78
    DragonMagazine
    -0.77
    ãĥ¼ãĥĨãĤ£
    -0.77
    amel
    -0.74
    ð
    -0.71
    votes
    -0.70
    ortmund
    -0.70
    moil
    -0.70
    iversary
    -0.69
    POSITIVE LOGITS
     versatile
    1.47
     easy
    1.30
     forgiving
    1.21
     flexible
    1.21
     efficient
    1.20
     useful
    1.19
     expensive
    1.16
     interesting
    1.14
     addictive
    1.13
     difficult
    1.13
    Activations Density 0.150%

    No Known Activations