© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 3372
    Prev
    Next
    INDEX
    Explanations

    materials used in construction, such as steel, aluminum, zinc, and glass

    oai_token-act-pair · gpt-3.5-turbo

    materials and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pause
    -0.81
     Hungry
    -0.78
     Rankings
    -0.77
    ults
    -0.75
     celebrations
    -0.74
     entertained
    -0.74
     visitation
    -0.73
    pause
    -0.73
    Alert
    -0.72
    ezvous
    -0.72
    POSITIVE LOGITS
     aluminium
    1.55
     alloy
    1.54
     resin
    1.53
     aluminum
    1.52
     acrylic
    1.50
     plastics
    1.46
     metals
    1.46
     polymer
    1.45
     steel
    1.45
     ceramic
    1.40
    Activations Density 0.495%

    No Known Activations