© 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. 10-RES-JB
    11. 2869
    Prev
    Next
    INDEX
    Explanations

    words related to types of occupations or specific roles, especially common in a household setting

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "house," particularly in various contexts related to domesticity and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICAL
    -0.72
     guiActiveUn
    -0.72
    uyomi
    -0.69
    istical
    -0.68
    aneously
    -0.67
    DragonMagazine
    -0.67
     CNS
    -0.64
    gey
    -0.64
    nir
    -0.64
    NetMessage
    -0.63
    POSITIVE LOGITS
    wives
    1.69
    wife
    1.67
    keeping
    1.50
    keeper
    1.30
    warming
    1.26
    mates
    1.24
    keepers
    1.20
    plant
    1.14
    maid
    1.13
    mate
    1.12
    Activations Density 0.045%

    No Known Activations