© 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. 20867
    Prev
    Next
    INDEX
    Explanations

    phrases related to support, nurturing, caring, leadership, and positive relationships

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to support, community, and positive 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
    VK
    -0.73
    ibur
    -0.72
    govtrack
    -0.70
     counterfe
    -0.70
    agate
    -0.67
     Manufact
    -0.67
     arsen
    -0.66
    urrection
    -0.66
    lat
    -0.65
    ucc
    -0.65
    POSITIVE LOGITS
     mentor
    0.98
     mentors
    0.95
     counselors
    0.95
     demeanor
    0.95
     parenting
    0.92
     caregivers
    0.91
     counselor
    0.90
     upbringing
    0.90
     nurturing
    0.87
     helpers
    0.83
    Activations Density 0.336%

    No Known Activations