© 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. 6-RES-JB
    11. 10760
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "care" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to care-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĥī
    -0.86
    obin
    -0.73
     poppy
    -0.68
     perjury
    -0.62
    NPR
    -0.61
    DX
    -0.61
    integer
    -0.61
     rand
    -0.61
    irty
    -0.61
    RESULTS
    -0.60
    POSITIVE LOGITS
    taker
    1.39
    fully
    1.05
    ful
    0.97
    tta
    0.95
    giving
    0.95
    er
    0.93
    care
    0.92
    taking
    0.88
    lli
    0.87
    ndra
    0.85
    Activations Density 0.017%

    No Known Activations