© 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. 11920
    Prev
    Next
    INDEX
    Explanations

    adverbs modifying verbs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "almost" indicating approximation or uncertainty

    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
     sclerosis
    -0.74
    oit
    -0.71
    ACTED
    -0.68
     Distribut
    -0.67
    ä¸Ń
    -0.65
    osition
    -0.64
    agate
    -0.63
    Ô
    -0.62
    liction
    -0.61
     RTX
    -0.60
    POSITIVE LOGITS
     certainly
    1.24
     exclusively
    1.12
     universally
    1.04
     invariably
    1.02
     uniformly
    0.97
     immediately
    0.96
     entirely
    0.95
     unanimously
    0.93
     instantly
    0.91
     unbelievably
    0.91
    Activations Density 0.038%

    No Known Activations