© 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. 20809
    Prev
    Next
    INDEX
    Explanations

    phrases referring to diverse groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to inclusivity across various demographics

    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
    LESS
    -0.83
    potion
    -0.69
    atl
    -0.60
    parser
    -0.60
    unn
    -0.59
    PP
    -0.59
     IPM
    -0.57
    lessly
    -0.57
    pmwiki
    -0.57
     Mole
    -0.57
    POSITIVE LOGITS
     faiths
    1.34
     genders
    1.31
     backgrounds
    1.27
     ages
    1.24
     stripes
    1.16
     genres
    1.11
     age
    1.11
     sexes
    1.11
     religions
    1.10
     denominations
    1.10
    Activations Density 0.191%

    No Known Activations