© 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. 2023
    Prev
    Next
    INDEX
    Explanations

    terms related to cuts in Social Security and retirement age adjustments in political contexts

    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
    674
    +0.20
    0.6%
    1967
    +0.11
    0.3%
    1343
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.20
    0.04
    536
    +0.11
    0.02
    138
    +0.10
    0.04
    Negative Logits
    WebElementEntity
    -0.55
     betweenstory
    -0.55
    RectangleBorder
    -0.54
     Strukt
    -0.53
     متعلقه
    -0.53
     AssemblyVersion
    -0.52
    menuStrip
    -0.52
    Hentet
    -0.51
     ***!
    -0.50
    StoryboardSegue
    -0.50
    POSITIVE LOGITS
     gaily
    0.82
     shewn
    0.82
     friable
    0.80
     nutella
    0.80
     vainly
    0.77
     unve
    0.77
     withal
    0.76
     cushi
    0.76
     tolerably
    0.74
     🤣🤣
    0.74
    Activations Density 0.236%

    No Known Activations