© 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. 1-RES-JB
    6. 22495
    Prev
    Next
    INDEX
    Explanations

    chemical and material terms, such as polymers and resins

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various types of polymers and related materials

    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
    atti
    -0.75
    earth
    -0.75
     attendants
    -0.73
    Sax
    -0.70
    erey
    -0.70
     Manor
    -0.69
    yth
    -0.67
     heirs
    -0.67
    swick
    -0.67
    enhagen
    -0.67
    POSITIVE LOGITS
     polymer
    1.25
     beads
    1.00
     resin
    1.00
     bead
    0.95
     plastics
    0.95
     latex
    0.92
     thinner
    0.91
     coating
    0.85
     acrylic
    0.84
     clay
    0.82
    Activations Density 0.025%

    No Known Activations