© 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. 10177
    Prev
    Next
    INDEX
    Explanations

    mentions of construction and development projects in a community setting

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to urban development and construction plans

    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
    nikov
    -0.80
    pkg
    -0.78
    uria
    -0.77
     pse
    -0.76
    opath
    -0.73
    wcsstore
    -0.72
     congratulations
    -0.72
     antibodies
    -0.71
    ERROR
    -0.69
     whip
    -0.67
    POSITIVE LOGITS
     existing
    1.18
     waterfront
    1.17
     redevelop
    1.13
     downtown
    1.10
     redevelopment
    1.06
     adjacent
    1.05
     leased
    1.03
     plaza
    1.03
     roadway
    1.02
     vacated
    0.99
    Activations Density 0.444%

    No Known Activations