© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 6303
    Prev
    Next
    INDEX
    Explanations

    words related to construction material and techniques, specifically compressed earth blocks

    oai_token-act-pair · gpt-3.5-turbo

    references to construction materials and methods, specifically related to compressed earth blocks

    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
    iannopoulos
    -0.88
     Patron
    -0.87
     Starship
    -0.86
     Transgender
    -0.85
     Vlad
    -0.82
    voice
    -0.78
     Nikki
    -0.77
     hostage
    -0.74
    yssey
    -0.72
    asus
    -0.72
    POSITIVE LOGITS
     soils
    1.85
     soil
    1.81
     gravel
    1.68
     manure
    1.67
     compost
    1.62
     clay
    1.52
     vegetation
    1.49
     fertilizer
    1.46
     weeds
    1.45
     lawn
    1.42
    Activations Density 0.406%

    No Known Activations