© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3486
    Prev
    Next
    INDEX
    Explanations

    political terms and names, especially related to allegations and opinions related to politics

    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
    1516
    +0.12
    0.4%
    597
    +0.11
    0.4%
    1331
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1516
    +0.12
    0.04
    1331
    +0.11
    0.04
    789
    +0.11
    0.03
    Negative Logits
    Cormack
    -0.77
    Allister
    -0.70
    Millan
    -0.58
    Leod
    -0.54
    Mahon
    -0.53
    Dermott
    -0.52
    Dowell
    -0.52
    Namara
    -0.50
     BigInt
    -0.50
     form
    -0.49
    POSITIVE LOGITS
    Mc
    1.25
     Mc
    1.25
     Sén
    1.13
     mc
    1.09
     kac
    1.08
     Mâ
    1.08
     makro
    1.07
     mcd
    1.06
     kask
    1.06
     siff
    1.06
    Activations Density 0.094%

    No Known Activations