© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11824
    Prev
    Next
    INDEX
    Explanations

    statistics and discussions related to poverty and economic disparities

    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
    241
    +0.13
    0.5%
    1624
    +0.12
    0.4%
    437
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.13
    0.02
    437
    +0.12
    0.02
    1241
    +0.10
    0.02
    Negative Logits
     reluct
    -0.68
     unve
    -0.67
     berea
    -0.66
     indestru
    -0.66
     seclu
    -0.66
     depic
    -0.64
     volunte
    -0.64
     impractica
    -0.63
     disagre
    -0.62
     unden
    -0.62
    POSITIVE LOGITS
     poverty
    1.20
    poverty
    1.05
     Poverty
    1.05
    Poverty
    0.91
     pobreza
    0.76
     îna
    0.57
     cebola
    0.55
     Championnat
    0.55
     scă
    0.54
     vescovo
    0.54
    Activations Density 0.071%

    No Known Activations