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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7769
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to allowing or permitting certain actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to discrimination based on sexual orientation and religious freedom

    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
    DragonMagazine
    -0.86
     Subtle
    -0.85
     Whilst
    -0.81
     realise
    -0.76
    uckland
    -0.76
     Aires
    -0.75
     Osw
    -0.73
    ruary
    -0.72
     whilst
    -0.71
    alling
    -0.71
    POSITIVE LOGITS
     federally
    1.19
     abortions
    1.08
     nonprofits
    1.06
     nonprofit
    1.01
     federal
    0.98
     contraceptives
    0.97
     religious
    0.94
     unlawful
    0.91
     certain
    0.91
     minors
    0.91
    Activations Density 0.495%

    No Known Activations