Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15996
    Prev
    Next
    INDEX
    Explanations

    points related to political engagement and activism

    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
    2019
    +0.13
    0.4%
    1415
    +0.11
    0.3%
    1265
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1921
    +0.13
    0.05
    166
    +0.11
    0.04
    1415
    +0.09
    0.03
    Negative Logits
     Mémoires
    -1.35
     Græ
    -1.31
     exé
    -1.26
     makro
    -1.26
     Kategor
    -1.25
     antik
    -1.25
     saar
    -1.24
     silikon
    -1.24
     Bibl
    -1.23
     kaos
    -1.23
    POSITIVE LOGITS
     enjoy
    1.05
     let
    0.98
     keep
    0.96
     continue
    0.95
     try
    0.95
     make
    0.95
     consider
    0.94
     prepare
    0.93
     decide
    0.93
     get
    0.93
    Activations Density 0.257%

    No Known Activations