© 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 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. 15445
    Prev
    Next
    INDEX
    Explanations

    positive adjectives

    oai_token-act-pair · gpt-3.5-turbo

    positive adjectives describing experiences and events

    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
    docs
    -0.89
    gans
    -0.87
     actionGroup
    -0.87
    Downloadha
    -0.85
    links
    -0.83
    arthed
    -0.80
    styles
    -0.80
    units
    -0.78
    bryce
    -0.77
    ouls
    -0.73
    POSITIVE LOGITS
     opportunity
    1.28
     reminder
    1.23
     coincidence
    1.23
     thing
    1.19
     testament
    1.17
     accomplishment
    1.16
     irony
    1.13
     lesson
    1.12
     moment
    1.11
     pity
    1.10
    Activations Density 0.140%

    No Known Activations