Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 3872
    Prev
    Next
    INDEX
    Explanations

    references to outdoor spaces, specifically focusing on the concept of a yard

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "yard."

    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
     Addiction
    -0.72
     Fusion
    -0.70
    Insert
    -0.70
    iq
    -0.66
     Duo
    -0.65
    ogen
    -0.64
    ogens
    -0.63
    achi
    -0.63
     Conan
    -0.62
    ami
    -0.61
    POSITIVE LOGITS
     yard
    4.03
    yard
    2.55
     yards
    2.49
    yards
    2.29
     Yard
    2.23
     Yards
    1.96
     backyard
    1.47
     lawn
    1.40
     porch
    1.31
     garden
    1.24
    Activations Density 0.010%

    No Known Activations