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

    Neuronpedia

    Jacobian LensNEW
    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. 5823
    Prev
    Next
    INDEX
    Explanations

    phrases related to neutrality and political stances

    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
    316
    +0.13
    0.5%
    966
    +0.13
    0.5%
    538
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.13
    0.02
    1363
    +0.13
    0.02
    420
    +0.12
    0.02
    Negative Logits
     lele
    -0.79
     ohr
    -0.76
     Amerik
    -0.73
     uhr
    -0.73
     thuy
    -0.71
     seiz
    -0.68
     dises
    -0.67
     „,
    -0.67
     kram
    -0.66
     vns
    -0.66
    POSITIVE LOGITS
     neutral
    1.45
    neutral
    1.40
     Neutral
    1.37
    Neutral
    1.36
     neutrality
    1.25
     Neutr
    1.03
    UTRAL
    0.97
     neutrals
    0.95
     нейтра
    0.91
     neutralize
    0.88
    Activations Density 0.073%

    No Known Activations