© 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. 5253
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Father."

    oai_token-act-pair · gpt-3.5-turbo

    references to fatherhood

    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
    mble
    -0.84
     externalToEVAOnly
    -0.69
    atility
    -0.69
    aneously
    -0.66
    aeda
    -0.65
    psey
    -0.65
    AW
    -0.64
    CONT
    -0.63
     uptake
    -0.63
    eers
    -0.61
    POSITIVE LOGITS
    hood
    1.15
     patriarch
    0.98
    father
    0.91
    hetical
    0.89
    volent
    0.89
    hesis
    0.86
    less
    0.73
    land
    0.73
    hes
    0.72
    mares
    0.72
    Activations Density 0.034%

    No Known Activations