© 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 · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14908
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms and concepts

    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
    1127
    +0.10
    0.3%
    143
    +0.09
    0.3%
    80
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1127
    +0.10
    0.04
    342
    +0.09
    0.05
    1861
    +0.09
    0.06
    Negative Logits
     nomine
    -1.07
     „,
    -1.04
     aen
    -1.04
     mef
    -1.03
     ivi
    -1.03
     doman
    -1.02
     igno
    -1.00
     meis
    -1.00
     apparti
    -0.99
     lyon
    -0.99
    POSITIVE LOGITS
     than
    1.48
    than
    1.21
    Than
    1.11
     niż
    1.07
     THAN
    1.05
     compared
    1.03
     Than
    1.02
     hơn
    1.02
     decât
    1.02
    THAN
    0.93
    Activations Density 0.628%

    No Known Activations