© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17579
    Prev
    Next
    INDEX
    Explanations

    adjectives that express positive qualities such as prettiness, craziness, funniness, and tidiness

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives related to aesthetics and humor

    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
     Augusta
    -0.59
    ãĥģ
    -0.55
     ALP
    -0.55
    TA
    -0.54
     pairs
    -0.53
    GA
    -0.52
    ãĤ¬
    -0.52
     ATP
    -0.52
     Tours
    -0.52
     inserted
    -0.51
    POSITIVE LOGITS
    iest
    2.35
    ily
    2.15
    iness
    2.05
    ier
    1.96
    ies
    1.81
    ying
    1.70
    iful
    1.68
    ied
    1.65
    ifully
    1.48
    ieth
    1.38
    Activations Density 0.185%

    No Known Activations