© 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. 14798
    Prev
    Next
    INDEX
    Explanations

    phrases related to socio-economic impacts and effects

    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
    1
    +0.08
    0.2%
    90
    +0.07
    0.2%
    1804
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    871
    +0.08
    0.03
    32
    +0.07
    0.03
    1392
    +0.07
    0.03
    Negative Logits
     wattpad
    -0.73
     disreg
    -0.72
     bonjour
    -0.69
     emphat
    -0.69
     endom
    -0.68
     inappro
    -0.68
     compen
    -0.67
     héro
    -0.66
     intrigu
    -0.66
     indestru
    -0.65
    POSITIVE LOGITS
     impact
    0.86
     effect
    0.77
     impacts
    0.71
     effects
    0.70
    impact
    0.69
     affect
    0.68
     implications
    0.67
    effect
    0.66
     consequences
    0.62
     Impact
    0.61
    Activations Density 0.173%

    No Known Activations