© 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. 11-RES-JB
    6. 1767
    Prev
    Next
    INDEX
    Explanations

    terms related to negative consequences or impacts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to environmental impacts and consequences

    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
    ppa
    -1.01
    enf
    -0.80
    onyms
    -0.77
    thia
    -0.77
    Laughs
    -0.77
    è£
    -0.73
    fuck
    -0.72
    dds
    -0.71
    apest
    -0.70
    ÃŃ
    -0.69
    POSITIVE LOGITS
     inaction
    1.23
     prolonged
    1.07
     improper
    1.05
     unchecked
    1.04
     declining
    1.04
     excessive
    1.03
     globalization
    1.02
     implementing
    1.00
     inadequate
    0.99
     adopting
    0.98
    Activations Density 0.193%

    No Known Activations