© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 826
    Prev
    Next
    INDEX
    Explanations

    words related to family members or relatives

    oai_token-act-pair · gpt-3.5-turbo

    references to family relationships, particularly the term "relatives."

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

    No Comments

    Negative Logits
    oker
    -0.76
     Patton
    -0.68
     Archdemon
    -0.67
    ococ
    -0.67
    Laun
    -0.66
    storm
    -0.66
    oted
    -0.66
     davidjl
    -0.65
    iman
    -0.65
    whe
    -0.62
    POSITIVE LOGITS
     relatives
    0.99
    hips
    0.94
    heses
    0.87
    hetical
    0.84
    hesis
    0.82
    folk
    0.82
    hetically
    0.77
    ilial
    0.77
     dolls
    0.76
    irtual
    0.76
    Activations Density 0.017%

    No Known Activations