© 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. 11-RES-JB
    11. 4243
    Prev
    Next
    INDEX
    Explanations

    words associated with negative attitudes and discrimination, such as prejudice, bigotry, hatred, and racism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to discrimination and social injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITNESS
    -0.97
    ullivan
    -0.72
     skelet
    -0.66
     refresh
    -0.66
     Expend
    -0.65
     Prospect
    -0.63
    selected
    -0.62
    cise
    -0.61
    issan
    -0.60
    uscript
    -0.60
    POSITIVE LOGITS
    ophobia
    1.24
     toward
    1.17
     towards
    1.15
     perpetrated
    1.11
     plag
    1.09
     perv
    1.05
     inherent
    1.00
     ingrained
    0.99
     inflicted
    0.98
     prevalent
    0.96
    Activations Density 0.127%

    No Known Activations