© 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 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. 7-RES-JB
    11. 20756
    Prev
    Next
    INDEX
    Explanations

    words related to love and getting to know people

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to love and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    monary
    -0.74
    vu
    -0.71
    interstitial
    -0.71
    mortem
    -0.68
    route
    -0.66
    brainer
    -0.66
    nings
    -0.65
    wcs
    -0.65
    ocking
    -0.65
    quart
    -0.64
    POSITIVE LOGITS
     him
    1.11
     Him
    1.08
     them
    1.04
     oneself
    1.02
     someone
    1.01
     somebody
    0.99
     Them
    0.97
     others
    0.94
     Yourself
    0.93
     yourself
    0.92
    Activations Density 0.310%

    No Known Activations