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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 23040
    Prev
    Next
    INDEX
    Explanations

    mentions of racial issues or disparities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to racial issues and discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ertodd
    -0.90
    tower
    -0.80
    kens
    -0.78
    ipop
    -0.78
    20439
    -0.78
    amina
    -0.75
    stadt
    -0.75
    icular
    -0.75
    hran
    -0.74
    uden
    -0.73
    POSITIVE LOGITS
     slurs
    1.26
    ized
    1.10
     minorities
    1.02
     prejudice
    1.01
     disparities
    0.99
     profiling
    0.98
     discrimination
    0.98
     disparity
    0.95
     animosity
    0.94
     stereotypes
    0.94
    Activations Density 0.035%

    No Known Activations