© 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
    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. 13978
    Prev
    Next
    INDEX
    Explanations

    words related to physical structures, particularly roofs

    oai_token-act-pair · gpt-3.5-turbo

    references to roofs and their conditions or characteristics

    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
     Andromeda
    -0.71
     Matters
    -0.67
     Disciple
    -0.66
    action
    -0.65
    Clar
    -0.64
    include
    -0.63
     Analog
    -0.61
    actions
    -0.61
     Deter
    -0.61
    conf
    -0.60
    POSITIVE LOGITS
     roof
    3.86
     roofs
    3.14
     Roof
    2.19
     rooftop
    2.10
     rooft
    2.01
     ceiling
    1.64
     balcony
    1.51
     attic
    1.45
     ceilings
    1.41
     floor
    1.34
    Activations Density 0.014%

    No Known Activations