© 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. 13875
    Prev
    Next
    INDEX
    Explanations

    phrases related to news events and actions taken

    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
    2019
    +0.12
    0.4%
    1806
    +0.10
    0.3%
    50
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1806
    +0.12
    0.06
    239
    +0.10
    0.05
    1921
    +0.10
    0.06
    Negative Logits
     noël
    -0.99
     exé
    -0.93
     soggior
    -0.93
     broderie
    -0.91
     poulet
    -0.89
     dégust
    -0.89
     prétend
    -0.89
     répon
    -0.85
     accompagne
    -0.85
     tricot
    -0.84
    POSITIVE LOGITS
     vowed
    0.72
     expects
    0.70
     believes
    0.70
     encourages
    0.69
     wished
    0.69
     wondered
    0.69
     acknowledges
    0.67
     anticipates
    0.66
     recommends
    0.65
     considers
    0.65
    Activations Density 0.339%

    No Known Activations