© 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. 5932
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of freedom and decision-making

    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
    1533
    +0.09
    0.2%
    1842
    +0.08
    0.2%
    1579
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    691
    +0.09
    0.01
    1509
    +0.08
    0.03
    17
    +0.08
    0.03
    Negative Logits
     fta
    -1.31
     thut
    -1.21
     ftu
    -1.20
     aen
    -1.19
     fte
    -1.19
     Keny
    -1.17
     dises
    -1.16
     effe
    -1.15
     mef
    -1.14
     volunte
    -1.13
    POSITIVE LOGITS
     freely
    0.91
     freedom
    0.70
     without
    0.63
     whatever
    0.62
    Điều
    0.59
     wherever
    0.59
     free
    0.57
     liberty
    0.56
     libertad
    0.56
    kháu
    0.54
    Activations Density 0.340%

    No Known Activations