© 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. 3585
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics and government

    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
    1150
    +0.12
    0.3%
    227
    +0.11
    0.3%
    297
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.12
    0.05
    1150
    +0.11
    0.02
    297
    +0.10
    0.04
    Negative Logits
     oleo
    -1.03
     fup
    -1.03
     tupperware
    -1.01
     philips
    -0.97
     ftu
    -0.97
     fta
    -0.97
     murano
    -0.97
     tranf
    -0.96
     bordeaux
    -0.95
     thut
    -0.94
    POSITIVE LOGITS
     bestseller
    0.70
     book
    0.69
     bestselling
    0.69
    ISBN
    0.68
     memoir
    0.68
     books
    0.65
     ISBN
    0.63
     Books
    0.59
     novels
    0.58
     paperback
    0.57
    Activations Density 0.305%

    No Known Activations