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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21061
    Prev
    Next
    INDEX
    Explanations

    words related to urban development and city infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    instances of challenges related to urban maintenance and improvement

    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
     behaving
    -0.70
    ocent
    -0.69
     nods
    -0.69
    soType
    -0.68
     circulation
    -0.67
     promo
    -0.67
     Prom
    -0.66
    cknow
    -0.66
     Gifts
    -0.64
     behaved
    -0.61
    POSITIVE LOGITS
     cumbersome
    1.35
     ardu
    1.29
     costly
    1.27
     prohib
    1.26
     tedious
    1.22
     expensive
    1.19
     daunting
    1.18
     tricky
    1.14
     burdens
    1.14
     painstaking
    1.12
    Activations Density 0.420%

    No Known Activations