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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13663
    Prev
    Next
    INDEX
    Explanations

    adverbs or adjectives starting with the word "seemingly."

    oai_token-act-pair · gpt-3.5-turbo

    the word "seemingly" along with phrases indicating uncertainty or observation

    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
    ription
    -0.80
    ioch
    -0.76
    iq
    -0.71
    awks
    -0.71
     Drill
    -0.70
    ogi
    -0.70
     Regions
    -0.70
    endered
    -0.68
    ogy
    -0.67
    alez
    -0.66
    POSITIVE LOGITS
     innocuous
    1.24
     unstoppable
    1.09
     unrelated
    1.07
     limitless
    1.06
     endless
    1.05
     oblivious
    1.05
     insur
    1.01
     contradictory
    0.97
     harmless
    0.97
     invincible
    0.97
    Activations Density 0.051%

    No Known Activations