© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23500
    Prev
    Next
    INDEX
    Explanations

    words related to recycling

    oai_token-act-pair · gpt-3.5-turbo

    terms related to recycling and sustainability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    htar
    -0.79
    insula
    -0.76
    ãĥĦ
    -0.71
    ihad
    -0.70
    ellen
    -0.70
    quart
    -0.70
    witz
    -0.70
     assassinated
    -0.67
    inen
    -0.66
    pass
    -0.63
    POSITIVE LOGITS
     bins
    1.13
     recycle
    1.05
    ycle
    1.01
     recycling
    1.00
     recy
    0.97
     recycled
    0.88
     cans
    0.84
     Waste
    0.82
    ibles
    0.81
     plastics
    0.80
    Activations Density 0.045%

    No Known Activations