© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14283
    Prev
    Next
    INDEX
    Explanations

    references to racial issues or discrimination

    oai_token-act-pair · gpt-3.5-turbo

    references to racial issues and profiling

    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
    ertodd
    -0.89
    tower
    -0.84
    hran
    -0.75
    amina
    -0.75
    Pad
    -0.74
    20439
    -0.73
    uden
    -0.73
     Mub
    -0.72
    icular
    -0.72
    ilton
    -0.72
    POSITIVE LOGITS
     slurs
    1.26
     profiling
    1.11
    ized
    1.09
     minorities
    1.09
     prejudice
    1.07
     discrimination
    1.03
     disparities
    1.01
     animosity
    0.99
     injustice
    0.98
     stereotypes
    0.96
    Activations Density 0.031%

    No Known Activations