© 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. 11-RES-JB
    11. 7698
    Prev
    Next
    INDEX
    Explanations

    descriptions related to visual styles and flavors

    oai_token-act-pair · gpt-3.5-turbo

    elements related to regional characteristics and cultural influences

    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
    pointers
    -0.75
    LESS
    -0.74
    anges
    -0.73
    thens
    -0.73
    cigarettes
    -0.72
    mits
    -0.70
    ateurs
    -0.68
    quart
    -0.66
    hots
    -0.65
    ometimes
    -0.65
    POSITIVE LOGITS
     flair
    1.42
     vibe
    1.40
     flavour
    1.40
     aspect
    1.31
     flavor
    1.28
     twist
    1.19
     element
    1.19
     tone
    1.18
     feel
    1.17
     nature
    1.15
    Activations Density 0.347%

    No Known Activations