© 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. 7371
    Prev
    Next
    INDEX
    Explanations

    words related to physical structures, particularly buildings

    oai_token-act-pair · gpt-3.5-turbo

    references to buildings and their condition

    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
    -0.98
    CHAT
    -0.76
    vous
    -0.73
    sha
    -0.73
    ño
    -0.72
    tle
    -0.70
     Nadu
    -0.70
    owder
    -0.67
    sweet
    -0.65
    Consumer
    -0.64
    POSITIVE LOGITS
     buildings
    1.15
    raper
    1.06
     erected
    1.02
     Buildings
    0.99
     blocks
    0.96
     skysc
    0.94
     constructed
    0.87
    chool
    0.86
     dwellings
    0.84
     building
    0.83
    Activations Density 0.029%

    No Known Activations