© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12794
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and economic interests

    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
    1265
    +0.17
    0.6%
    1323
    +0.15
    0.5%
    168
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.17
    0.03
    990
    +0.15
    0.03
    1265
    +0.13
    0.03
    Negative Logits
     erec
    -0.66
     haba
    -0.58
     robus
    -0.56
     Politica
    -0.55
     alis
    -0.54
     adul
    -0.54
     ë
    -0.53
     territo
    -0.52
     huma
    -0.52
     socie
    -0.51
    POSITIVE LOGITS
     interests
    1.26
    interests
    1.17
    Interests
    1.12
     Interest
    1.12
     interest
    1.11
     Interests
    1.10
    interest
    1.04
    Interest
    1.02
     INTEREST
    0.90
    INTEREST
    0.85
    Activations Density 0.054%

    No Known Activations