© 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. 11-RES-JB
    11. 10216
    Prev
    Next
    INDEX
    Explanations

    terms related to waste management and recycling

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to recycling and waste management

    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
    iazep
    -1.04
    Ax
    -0.90
     Templar
    -0.87
    >[
    -0.86
     Mattis
    -0.85
    Intel
    -0.84
    Iran
    -0.83
    afort
    -0.82
     Caucasus
    -0.82
     Malk
    -0.80
    POSITIVE LOGITS
     recycling
    2.18
     landfill
    2.09
     recy
    2.07
     recycle
    2.04
     compost
    2.03
     recycled
    1.79
     waste
    1.70
     Waste
    1.65
     trash
    1.63
     rubbish
    1.61
    Activations Density 0.336%

    No Known Activations