Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 20530
    Prev
    Next
    INDEX
    Explanations

    words related to social issues, injustice, and disparities in society

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social inequality and the marginalized

    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
    arate
    -0.75
     Rica
    -0.74
    boa
    -0.68
    wide
    -0.68
    irting
    -0.67
    arettes
    -0.66
    fw
    -0.65
    ä¿
    -0.65
    oya
    -0.65
    OIL
    -0.64
    POSITIVE LOGITS
     masses
    1.04
    cients
    1.03
     populace
    0.96
     psyche
    0.92
    liest
    0.90
     arts
    0.90
     unemployed
    0.88
     sciences
    0.88
     ones
    0.87
    hest
    0.83
    Activations Density 0.312%

    No Known Activations