© 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. 12-RES-JB
    11. 4441
    Prev
    Next
    INDEX
    Explanations

    descriptions of urban neighborhoods or locations, possibly focusing on changes or improvements over time

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to specific locations and urban development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    Äį
    -1.03
    Ireland
    -0.97
     Ukrainians
    -0.94
     sv
    -0.91
     Maced
    -0.89
    ���
    -0.89
    Å¡
    -0.87
    ̶
    -0.86
     Eston
    -0.85
    uania
    -0.84
    POSITIVE LOGITS
     Oakland
    2.51
    Oak
    2.22
     BART
    1.92
     Hayward
    1.90
     Berkeley
    1.84
    ameda
    1.59
     Raiders
    1.58
     Bay
    1.53
    Bay
    1.39
     Contra
    1.36
    Activations Density 0.335%

    No Known Activations