© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11348
    Prev
    Next
    INDEX
    Explanations

    phrases related to ethical treatment and responsibility

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and issues related to animal rights and ethics

    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
    bourg
    -0.59
    agne
    -0.57
     Archdemon
    -0.55
    anwhile
    -0.55
    avis
    -0.54
    erno
    -0.51
    ammy
    -0.51
    fire
    -0.49
    anka
    -0.47
    shapeshifter
    -0.46
    POSITIVE LOGITS
    ©
    0.55
    ©¶æ
    0.52
    rule
    0.47
    creen
    0.45
    ׾
    0.45
    Ó
    0.44
    romy
    0.44
    cedented
    0.43
    ackers
    0.43
    ×ŀ
    0.43
    Activations Density 0.395%

    No Known Activations