© 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 EvalsExportsinterp-engineNEWAPI 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. 4166
    Prev
    Next
    INDEX
    Explanations

    terms related to political figures, statements, and actions

    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
    1842
    +0.25
    0.7%
    184
    +0.10
    0.3%
    604
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.25
    0.02
    1919
    +0.10
    0.06
    392
    +0.10
    0.03
    Negative Logits
     impra
    -1.88
     disagre
    -1.88
     increa
    -1.85
     reluct
    -1.82
     maneu
    -1.79
     inev
    -1.75
     uninten
    -1.75
     encomp
    -1.71
     disreg
    -1.69
     tolerably
    -1.69
    POSITIVE LOGITS
     “
    1.06
     "
    0.99
     «
    0.94
    “
    0.82
     „
    0.81
     “[
    0.79
     "[
    0.77
     "'
    0.74
    「
    0.72
     ”
    0.70
    Activations Density 0.953%

    No Known Activations