© 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 · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 10736
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal contexts and regulations

    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
    1334
    +0.13
    0.5%
    172
    +0.13
    0.5%
    204
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.13
    0.04
    1334
    +0.13
    0.04
    1482
    +0.13
    0.04
    Negative Logits
     Derfor
    -0.68
     Viene
    -0.50
    Kas
    -0.49
    SAX
    -0.49
    Kra
    -0.48
     Román
    -0.48
     Kna
    -0.48
     Peti
    -0.48
    Kna
    -0.48
     Adicion
    -0.48
    POSITIVE LOGITS
     THOUGH
    0.97
    though
    0.87
     though
    0.84
     bismuth
    0.64
    Though
    0.63
     Though
    0.62
    jectures
    0.61
    ulir
    0.60
     affez
    0.57
    herjee
    0.57
    Activations Density 0.066%

    No Known Activations