© 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. 2-RES-JB
    11. 7399
    Prev
    Next
    INDEX
    Explanations

    words related to emotional reactions such as pity, trope, and sympathy

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to emotional concepts such as sympathy and pity

    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
    keeping
    -0.84
    artifacts
    -0.80
    runner
    -0.77
    epend
    -0.77
    keeper
    -0.76
    heast
    -0.75
    isitions
    -0.75
    ophon
    -0.74
    omb
    -0.73
    icators
    -0.72
    POSITIVE LOGITS
    pmwiki
    0.87
    é¾įå¥ij士
    0.86
    Anonymous
    0.83
    BuyableInstoreAndOnline
    0.77
     Publication
    0.76
    ilial
    0.74
    Fan
    0.73
     Ratings
    0.73
     Desk
    0.71
     sympathy
    0.71
    Activations Density 0.022%

    No Known Activations