© 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. 9162
    Prev
    Next
    INDEX
    Explanations

    elements related to basic human needs and fundamental rights, including shelter, health, employment, and discrimination

    oai_token-act-pair · gpt-3.5-turbo

    phrases connected to basic human needs and social issues

    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
     guiName
    -0.82
    owe
    -0.74
    quist
    -0.70
     Reported
    -0.69
    ._
    -0.67
    ight
    -0.64
    tsky
    -0.64
    ixel
    -0.63
    atch
    -0.63
    ources
    -0.61
    POSITIVE LOGITS
     etc
    1.71
    etc
    1.54
    whatever
    0.99
     ect
    0.85
     constitu
    0.80
    ĪĴ
    0.70
    âĢ¦)
    0.69
    76561
    0.68
     carbohyd
    0.66
     blah
    0.65
    Activations Density 0.225%

    No Known Activations