© 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 EvalsExportsinterp-engineNEWAPI 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. 21210
    Prev
    Next
    INDEX
    Explanations

    mentions of performing activities at home

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of home and personal space

    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
     resil
    -0.72
     Osw
    -0.65
    insula
    -0.65
     Rebell
    -0.64
    manac
    -0.63
    ggles
    -0.61
    icent
    -0.61
    itialized
    -0.59
    osi
    -0.58
     Tate
    -0.58
    POSITIVE LOGITS
    aneously
    0.99
     without
    0.89
     instead
    0.85
     rather
    0.85
     using
    0.80
     whenever
    0.78
     WITHOUT
    0.78
     via
    0.77
     whilst
    0.75
     anywhere
    0.75
    Activations Density 0.271%

    No Known Activations