© 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 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. 2-RES-JB
    11. 15648
    Prev
    Next
    INDEX
    Explanations

    mentions or locations of "Taksim" Square

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the location "Taksim" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸ¬
    -0.70
    ãĥ£
    -0.69
     Bleach
    -0.62
     ejac
    -0.61
    gravity
    -0.60
     Kitty
    -0.60
     redistributed
    -0.60
     bleach
    -0.60
     resusc
    -0.60
    physical
    -0.60
    POSITIVE LOGITS
    aks
    1.17
    unta
    1.09
    andr
    1.07
    ongs
    1.00
    udo
    0.93
    kins
    0.87
    akes
    0.87
    ames
    0.86
    meier
    0.86
    ota
    0.85
    Activations Density 0.013%

    No Known Activations