© 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
    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. 22366
    Prev
    Next
    INDEX
    Explanations

    words related to land

    oai_token-act-pair · gpt-3.5-turbo

    the term "land" in various contexts

    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
     Anonymous
    -0.70
    obin
    -0.67
    nc
    -0.67
    IO
    -0.67
    é¾įåĸļ士
    -0.65
    mins
    -0.65
     Dmit
    -0.65
    io
    -0.65
    bos
    -0.64
    iano
    -0.64
    POSITIVE LOGITS
     land
    3.78
     lands
    2.64
    Land
    2.21
     Land
    2.14
     Lands
    1.87
    land
    1.75
     landed
    1.70
     farmland
    1.59
     soil
    1.52
     landowners
    1.52
    Activations Density 0.017%

    No Known Activations