© 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. 3-RES-JB
    11. 22844
    Prev
    Next
    INDEX
    Explanations

    mentions of houses in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of a "house."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.80
    iferation
    -0.70
    DragonMagazine
    -0.69
     Archdemon
    -0.66
     CNS
    -0.66
     guiActiveUn
    -0.65
    aneously
    -0.65
     Nieto
    -0.63
    umbs
    -0.62
     footh
    -0.62
    POSITIVE LOGITS
    wife
    1.32
    wives
    1.24
    boat
    1.02
    keeping
    1.02
    warming
    1.01
    plant
    0.99
    boats
    0.97
    cle
    0.94
    keeper
    0.92
    marks
    0.90
    Activations Density 0.020%

    No Known Activations