© 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. 1-RES-JB
    11. 16814
    Prev
    Next
    INDEX
    Explanations

    words related to controversial political figures and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to torture and related historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ü
    -0.93
    âĸ¬
    -0.85
    ä
    -0.82
    à
    -0.80
    liest
    -0.78
    UAL
    -0.77
    ãĤ·
    -0.73
    Minecraft
    -0.72
    RGB
    -0.71
    ãĥī
    -0.71
    POSITIVE LOGITS
     Bolton
    0.84
     Tort
    0.82
    ramid
    0.81
    ongyang
    0.81
    ombo
    0.78
    kefeller
    0.77
    artisan
    0.77
    terness
    0.76
    odies
    0.75
    oreal
    0.75
    Activations Density 0.023%

    No Known Activations