© 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. 6-RES-JB
    11. 9662
    Prev
    Next
    INDEX
    Explanations

    words related to family and social relationships

    oai_token-act-pair · gpt-3.5-turbo

    mentions of relatives and family connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oted
    -0.77
    iasis
    -0.69
     SOC
    -0.63
     boots
    -0.62
    headed
    -0.60
     Capitalism
    -0.59
     Loch
    -0.58
    avery
    -0.57
    abad
    -0.57
    JS
    -0.57
    POSITIVE LOGITS
     relatives
    0.87
    hips
    0.85
    llah
    0.84
     remem
    0.82
    hetical
    0.81
    hetically
    0.79
    arten
    0.78
     acquaintances
    0.77
     describ
    0.73
     confir
    0.71
    Activations Density 0.086%

    No Known Activations