© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12857
    Prev
    Next
    INDEX
    Explanations

    phrases related to political campaigns and statements

    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
    198
    +0.12
    0.4%
    576
    +0.09
    0.2%
    1899
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    576
    +0.12
    0.04
    136
    +0.09
    0.01
    1899
    +0.08
    0.03
    Negative Logits
     impra
    -0.87
     increa
    -0.83
     encomp
    -0.80
     unspeak
    -0.79
     depic
    -0.73
     uninten
    -0.73
     affor
    -0.73
     disagre
    -0.73
     indescri
    -0.72
     inconce
    -0.71
    POSITIVE LOGITS
     usually
    1.03
    usually
    0.98
     typically
    0.91
    Usually
    0.88
     Usually
    0.87
    typically
    0.81
     normally
    0.77
    Typically
    0.76
     often
    0.75
     Typically
    0.75
    Activations Density 0.689%

    No Known Activations