© 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. 11390
    Prev
    Next
    INDEX
    Explanations

    locations or activities related to being inside a building

    oai_token-act-pair · gpt-3.5-turbo

    words related to indoor and outdoor environments

    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
    egu
    -0.69
     Consortium
    -0.68
     rewrite
    -0.66
     dispute
    -0.64
     fiat
    -0.64
     Claim
    -0.63
    ledge
    -0.63
    reements
    -0.63
     Payment
    -0.63
     fork
    -0.62
    POSITIVE LOGITS
     outdoors
    3.77
     indoors
    3.70
     indoor
    2.23
     outdoor
    1.88
     Outdoor
    1.70
     upstairs
    1.60
     downstairs
    1.50
    doors
    1.18
     uphill
    1.11
     humidity
    1.10
    Activations Density 0.027%

    No Known Activations