© 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. 9-RES-JB
    11. 7343
    Prev
    Next
    INDEX
    Explanations

    information related to urban development and renovation projects

    oai_token-act-pair · gpt-3.5-turbo

    references to urban development and real estate projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     epist
    -0.85
    ghazi
    -0.79
     Virus
    -0.78
     Franç
    -0.77
    idepress
    -0.77
     pir
    -0.73
    jab
    -0.73
     persecuted
    -0.72
     scept
    -0.72
     WikiLeaks
    -0.72
    POSITIVE LOGITS
     redevelopment
    1.60
     redevelop
    1.48
    Construction
    1.42
     zoning
    1.42
     renovations
    1.39
     renovation
    1.36
     landsc
    1.31
     architectural
    1.28
     relocation
    1.23
     Architects
    1.21
    Activations Density 1.314%

    No Known Activations