© 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. 7251
    Prev
    Next
    INDEX
    Explanations

    words related to political trends and sentiments

    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
    872
    +0.17
    0.5%
    1343
    +0.10
    0.3%
    198
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.17
    0.06
    683
    +0.10
    0.06
    697
    +0.10
    0.05
    Negative Logits
    <bos>
    -0.45
    STERY
    -0.44
    unic
    -0.43
    addition
    -0.43
    epr
    -0.43
    mbH
    -0.42
    INTEN
    -0.41
    Poss
    -0.40
    instan
    -0.40
    axl
    -0.40
    POSITIVE LOGITS
     appunt
    0.88
     createSlice
    0.87
     autunno
    0.86
     borse
    0.80
     ufficio
    0.79
     appartamento
    0.79
     abbigliamento
    0.79
     soste
    0.76
     letti
    0.76
     ristor
    0.76
    Activations Density 0.397%

    No Known Activations