© 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. 13247
    Prev
    Next
    INDEX
    Explanations

    references to shifts or changes in a political context

    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
    61
    +0.11
    0.4%
    1870
    +0.11
    0.4%
    188
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.11
    0.03
    61
    +0.11
    0.02
    1506
    +0.11
    0.02
    Negative Logits
     péné
    -0.66
     Madura
    -0.60
     vogli
    -0.58
     avrebbero
    -0.50
     avete
    -0.49
     Puro
    -0.47
     avesse
    -0.47
     guadag
    -0.46
     Manus
    -0.46
     doveva
    -0.46
    POSITIVE LOGITS
     shift
    1.26
    shift
    1.25
     shifts
    1.17
     Shift
    1.17
    Shift
    1.12
    shifting
    1.08
     shifted
    1.07
     shifting
    1.07
    shifts
    1.03
     Shifts
    1.00
    Activations Density 0.076%

    No Known Activations