© 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. 0-RES-JB
    11. 1515
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cares" with a high level of activation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern or care towards people or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ja
    -0.68
     breakout
    -0.67
     explosive
    -0.65
     Rubin
    -0.64
    RPG
    -0.64
     Sil
    -0.61
     Reloaded
    -0.61
     Royale
    -0.60
    rocket
    -0.60
    ula
    -0.60
    POSITIVE LOGITS
     cares
    3.20
     cared
    2.75
     caring
    2.66
     care
    2.22
    care
    1.68
     CARE
    1.52
     Care
    1.51
    Care
    1.37
     mattered
    1.19
     caregivers
    1.04
    Activations Density 0.011%

    No Known Activations