© 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. 6566
    Prev
    Next
    INDEX
    Explanations

    word combinations related to social or political stances on controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    topics related to marriage and homosexuality, particularly from a religious or societal standpoint

    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
     Logged
    -0.90
    kj
    -0.83
    WER
    -0.83
    ngth
    -0.77
    ossal
    -0.75
    DragonMagazine
    -0.72
    ventures
    -0.72
    Crash
    -0.71
    senal
    -0.70
    irie
    -0.70
    POSITIVE LOGITS
     homosexuality
    1.91
     polygamy
    1.70
     contraception
    1.62
     adultery
    1.56
     incest
    1.55
     homosexual
    1.55
     homosexuals
    1.53
     sexuality
    1.51
     abortion
    1.48
     abortions
    1.45
    Activations Density 0.448%

    No Known Activations