© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 7810
    Prev
    Next
    INDEX
    Explanations

    words related to the chemical compound "poly"

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of polymers, specifically those starting with "poly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erves
    -0.93
    erve
    -0.87
    tesy
    -0.82
    taker
    -0.80
    andr
    -0.79
     Keen
    -0.77
     Rankings
    -0.77
    McC
    -0.76
    drivers
    -0.76
    CTV
    -0.73
    POSITIVE LOGITS
     poly
    3.56
    poly
    2.99
    Poly
    2.83
     Poly
    2.58
     polyg
    2.15
     monog
    1.65
     polymer
    1.60
     polygamy
    1.43
     mono
    1.40
     polymorph
    1.34
    Activations Density 0.032%

    No Known Activations