© 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. 10-RES-JB
    11. 2656
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal norms and biases, especially institutionalized ones

    oai_token-act-pair · gpt-3.5-turbo

    topics related to institutionalized biases and societal norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endment
    -0.92
    bernatorial
    -0.87
    etsk
    -0.84
    earch
    -0.80
     Gerr
    -0.78
    hire
    -0.76
    shall
    -0.76
    eday
    -0.75
    éĹ
    -0.74
    leased
    -0.74
    POSITIVE LOGITS
     stereotypes
    1.62
     prejudices
    1.57
     stereotype
    1.53
     precon
    1.48
     patriarchal
    1.46
     dehuman
    1.43
     ingrained
    1.43
     prejudice
    1.41
     stigma
    1.41
     subconscious
    1.41
    Activations Density 0.662%

    No Known Activations