© 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. 16361
    Prev
    Next
    INDEX
    Explanations

    mentions of outdoor spaces or objects related to outdoor spaces

    oai_token-act-pair · gpt-3.5-turbo

    references to lawns and related outdoor spaces

    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
     Released
    -0.71
     Torres
    -0.69
    ansen
    -0.66
     Suarez
    -0.65
    atsu
    -0.65
     Protocol
    -0.64
    Trans
    -0.64
    trans
    -0.64
     analysed
    -0.63
    anta
    -0.62
    POSITIVE LOGITS
     lawn
    3.83
     Lawn
    2.72
     landsc
    1.62
     porch
    1.61
     patio
    1.52
     garden
    1.52
     driveway
    1.51
     grass
    1.50
     gardens
    1.45
     yard
    1.36
    Activations Density 0.009%

    No Known Activations