© 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. 6193
    Prev
    Next
    INDEX
    Explanations

    phrases related to the impact of various factors on different aspects of society or the environment

    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
    990
    +0.07
    0.2%
    1253
    +0.07
    0.2%
    474
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    990
    +0.07
    0.04
    1002
    +0.07
    0.04
    413
    +0.07
    0.03
    Negative Logits
     reger
    -0.95
     meras
    -0.91
     rege
    -0.77
     patrio
    -0.77
     utop
    -0.77
     demen
    -0.77
     solidar
    -0.77
     bera
    -0.75
     zom
    -0.73
     auton
    -0.72
    POSITIVE LOGITS
     effect
    0.70
     effects
    0.70
     impact
    0.70
     Effect
    0.65
    Effect
    0.64
    effect
    0.63
     Effects
    0.61
     effets
    0.60
    Effects
    0.58
     impacts
    0.57
    Activations Density 0.171%

    No Known Activations