© 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. 11-RES-JB
    6. 20550
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations and land features

    oai_token-act-pair · gpt-3.5-turbo

    details about geographical regions and environmental impacts

    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
     Freddie
    -0.81
     Ghostbusters
    -0.77
     Wiz
    -0.75
    Doctors
    -0.74
     Weiner
    -0.74
     Balls
    -0.72
    iuses
    -0.71
     Doctors
    -0.70
     handcuffs
    -0.70
     Toys
    -0.70
    POSITIVE LOGITS
     biodiversity
    1.70
     vegetation
    1.61
     habitat
    1.59
     deforestation
    1.52
     habitats
    1.51
     ecological
    1.48
     soils
    1.46
     forests
    1.45
     ecology
    1.44
     ecosystems
    1.44
    Activations Density 0.793%

    No Known Activations