© 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. 2090
    Prev
    Next
    INDEX
    Explanations

    terms related to social issues and community concerns

    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
    1870
    +0.15
    0.5%
    1741
    +0.12
    0.4%
    468
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.15
    0.05
    1510
    +0.12
    0.05
    1870
    +0.12
    0.04
    Negative Logits
     impon
    -1.04
     ideolog
    -0.99
     solidar
    -0.94
     utop
    -0.93
     republi
    -0.90
    Solución
    -0.88
     sappi
    -0.87
     higien
    -0.85
     minimalis
    -0.83
     scopri
    -0.82
    POSITIVE LOGITS
     unspeak
    1.24
     indescri
    1.18
     inext
    1.17
     snoopy
    1.15
     hairc
    1.14
     cuck
    1.13
     gaily
    1.12
     Illus
    1.11
     apprehen
    1.11
     caprice
    1.10
    Activations Density 0.488%

    No Known Activations