© 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 · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6996
    Prev
    Next
    INDEX
    Explanations

    locations or events related to Dallas, Texas

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1573
    +0.13
    0.6%
    200
    +0.13
    0.5%
    1053
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    765
    +0.13
    0.02
    200
    +0.13
    0.02
    1573
    +0.13
    0.02
    Negative Logits
     ecru
    -0.53
    Przyp
    -0.52
    Wię
    -0.51
     groupName
    -0.49
    Razer
    -0.48
     Hodg
    -0.48
    Może
    -0.48
     Griswold
    -0.48
     Langdon
    -0.47
    página
    -0.47
    POSITIVE LOGITS
     Dallas
    1.40
    Dallas
    1.29
    ALLAS
    0.92
     kram
    0.91
     Cowboys
    0.91
     optik
    0.79
    vericks
    0.72
     Nguy
    0.72
     kaos
    0.72
     logis
    0.72
    Activations Density 0.121%

    No Known Activations