© 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. 2-RES-JB
    11. 17522
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating a strong degree or intensity, such as "downright" or "decidedly"

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers that convey strong emotions or judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.89
    ramid
    -0.89
    etheus
    -0.76
     Rapp
    -0.72
    etus
    -0.71
    ulton
    -0.70
    agents
    -0.69
    arta
    -0.68
    ACP
    -0.68
    encers
    -0.68
    POSITIVE LOGITS
    EngineDebug
    0.85
     downright
    0.81
    ãĤ¦ãĤ¹
    0.78
     Jagu
    0.77
     adventurous
    0.74
     dangerous
    0.74
     silly
    0.74
    BuyableInstoreAndOnline
    0.70
     awkward
    0.70
     embarrassing
    0.70
    Activations Density 0.005%

    No Known Activations