© 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. 2-RES-JB
    11. 10461
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of the interior of objects or spaces

    oai_token-act-pair · gpt-3.5-turbo

    references to "interior" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fortune
    -0.85
    thood
    -0.79
    tle
    -0.77
    SHIP
    -0.72
    ansky
    -0.72
    Ox
    -0.72
    arov
    -0.71
    fleet
    -0.69
    KING
    -0.68
    nir
    -0.67
    POSITIVE LOGITS
     interior
    1.06
     decoration
    0.90
     ministry
    0.90
    door
    0.83
     decor
    0.83
     perimeter
    0.82
     door
    0.82
     workings
    0.80
     seams
    0.79
     entrances
    0.77
    Activations Density 0.007%

    No Known Activations