© 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. 4-RES-JB
    11. 10638
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical locations, specifically basements

    oai_token-act-pair · gpt-3.5-turbo

    references to basements or cellar spaces

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

    No Comments

    Negative Logits
    nir
    -0.78
    acting
    -0.78
    utan
    -0.77
    Cola
    -0.76
    cific
    -0.72
    uncture
    -0.71
    itia
    -0.71
    uality
    -0.70
    HCR
    -0.68
    acted
    -0.68
    POSITIVE LOGITS
     basement
    1.14
    stairs
    0.94
     lid
    0.91
     cellar
    0.86
     hatch
    0.86
     Dwell
    0.85
     courtyard
    0.85
     attic
    0.84
     closet
    0.82
     bedroom
    0.80
    Activations Density 0.009%

    No Known Activations