© 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. 9-RES-JB
    11. 4632
    Prev
    Next
    INDEX
    Explanations

    text related to social issues, humanitarian efforts, and societal injustices

    oai_token-act-pair · gpt-3.5-turbo

    themes related to social justice and humanitarian issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcsstore
    -0.75
    Sty
    -0.74
    */(
    -0.73
     Flavoring
    -0.72
    ablishment
    -0.71
    querade
    -0.71
    andise
    -0.70
    asonic
    -0.68
     Guinness
    -0.68
    idity
    -0.67
    POSITIVE LOGITS
     orphans
    1.37
     oppressed
    1.34
     disadvantaged
    1.30
     homeless
    1.29
     impoverished
    1.29
     marginalized
    1.28
     survivors
    1.26
     suffering
    1.25
     victims
    1.25
     needy
    1.22
    Activations Density 2.000%

    No Known Activations