© 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. 11241
    Prev
    Next
    INDEX
    Explanations

    information related to family members like mothers, fathers, and children

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships, particularly those involving mothers and fathers

    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
     Flavoring
    -0.92
    BTC
    -0.84
    ioxide
    -0.83
    ALLY
    -0.81
    ĪĴ
    -0.76
    çIJ
    -0.75
    TEXTURE
    -0.74
    INAL
    -0.73
    ATIONS
    -0.69
     Stellar
    -0.65
    POSITIVE LOGITS
     daughters
    1.46
     daughter
    1.43
     grandmother
    1.42
    daughter
    1.38
     grandparents
    1.37
     dads
    1.31
     fathers
    1.28
     sons
    1.26
     dad
    1.24
     son
    1.23
    Activations Density 0.122%

    No Known Activations