© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 9941
    Prev
    Next
    INDEX
    Explanations

    descriptions of urban development projects including specifics like housing, retail spaces, office spaces, and other facilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to mixed-use development projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cens
    -0.89
    CLAIM
    -0.81
    ERROR
    -0.73
    Disclaimer
    -0.72
    Filename
    -0.72
    strings
    -0.72
    Reply
    -0.70
    othal
    -0.70
    Words
    -0.69
    Invalid
    -0.68
    POSITIVE LOGITS
     residences
    1.27
     offices
    1.25
     restrooms
    1.22
     apartments
    1.20
     classrooms
    1.16
     restaurants
    1.16
     condos
    1.16
     amenities
    1.15
     gardens
    1.15
     landsc
    1.14
    Activations Density 0.213%

    No Known Activations