© 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. 17164
    Prev
    Next
    INDEX
    Explanations

    words related to rooftops or construction

    oai_token-act-pair · gpt-3.5-turbo

    references to rooftops and their condition or characteristics

    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
     MacArthur
    -0.76
    avez
    -0.73
     Lauder
    -0.71
     Sacrament
    -0.69
    bourg
    -0.67
    Clar
    -0.66
    Americans
    -0.65
     Norn
    -0.65
    ISTER
    -0.64
    imens
    -0.64
    POSITIVE LOGITS
     roof
    1.06
    deck
    1.00
     rack
    0.91
     terr
    0.85
     racks
    0.84
     roofs
    0.83
    ilion
    0.83
     loft
    0.83
     tops
    0.82
     deck
    0.80
    Activations Density 0.010%

    No Known Activations