© 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. 9-RES-JB
    11. 23676
    Prev
    Next
    INDEX
    Explanations

    sentences related to social justice and discrimination

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to social justice issues and discrimination

    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
    luster
    -0.75
    ufact
    -0.72
     [|
    -0.71
    Engineers
    -0.67
    ipment
    -0.66
    ombo
    -0.65
    Legend
    -0.65
    ãĤ´ãĥ³
    -0.65
    ventory
    -0.64
    arbon
    -0.64
    POSITIVE LOGITS
     feminists
    1.30
     feminist
    1.24
     shaming
    1.23
     homophobic
    1.21
     Feminist
    1.19
     feminism
    1.18
     homophobia
    1.15
     dehuman
    1.14
     rapists
    1.12
     misogyn
    1.11
    Activations Density 1.852%

    No Known Activations