Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8801
    Prev
    Next
    INDEX
    Explanations

    phrases related to urban planning and development

    oai_token-act-pair · gpt-3.5-turbo

    plans and proposals related to urban 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
    ictionary
    -0.74
    arma
    -0.71
    cipl
    -0.71
    âĨ
    -0.70
    à¼
    -0.70
    FBI
    -0.69
    omial
    -0.69
    cue
    -0.68
    REP
    -0.67
    milo
    -0.66
    POSITIVE LOGITS
     renovations
    1.50
     redevelopment
    1.40
     redevelop
    1.32
     renovation
    1.31
     condos
    1.30
     renov
    1.24
     amenities
    1.21
     sidewalks
    1.21
     buildings
    1.18
     downtown
    1.18
    Activations Density 0.480%

    No Known Activations