© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 4311
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures with titles such as "mayor" or "Mayor."

    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
    555
    +0.13
    0.5%
    889
    +0.13
    0.5%
    1387
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1336
    +0.13
    0.03
    1387
    +0.13
    0.02
    555
    +0.13
    0.02
    Negative Logits
    Leod
    -0.50
    Hahahahaha
    -0.49
    uuuuu
    -0.49
    Cormack
    -0.47
    artney
    -0.47
    JsonInclude
    -0.47
    Allister
    -0.46
     prolly
    -0.45
    hermosa
    -0.45
    Ehh
    -0.44
    POSITIVE LOGITS
     Mayor
    1.39
     mayor
    1.37
    Mayor
    1.32
    mayor
    1.23
     mayors
    1.10
     MAYOR
    1.08
     mayoral
    1.05
     Municip
    0.75
     municipality
    0.65
     Bürgermeister
    0.65
    Activations Density 0.065%

    No Known Activations