© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9334
    Prev
    Next
    INDEX
    Explanations

    words related to the role of caregiving or caretaking

    oai_token-act-pair · gpt-3.5-turbo

    references to caregiving and caretakers

    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
    ãĥĥãĥī
    -0.66
    ï¸ı
    -0.60
    âĸ¬
    -0.60
    lihood
    -0.60
     Ventures
    -0.59
    icut
    -0.59
     AMERICA
    -0.59
    ãĥ³ãĤ¸
    -0.59
     Kamp
    -0.57
    kered
    -0.57
    POSITIVE LOGITS
    taker
    1.83
    giving
    1.46
    taking
    1.37
    free
    1.24
    lessness
    1.17
    lessly
    1.13
    ening
    1.08
    worn
    1.06
    rs
    0.99
    bear
    0.95
    Activations Density 0.036%

    No Known Activations