Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8455
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning events that happened over weekends

    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
    1145
    +0.12
    0.4%
    1306
    +0.11
    0.4%
    169
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.12
    0.03
    1993
    +0.11
    0.03
    1306
    +0.11
    0.02
    Negative Logits
     lunedì
    -0.60
     Décembre
    -0.59
     Luglio
    -0.56
     Quels
    -0.56
    🕗
    -0.55
     préc
    -0.55
     Février
    -0.54
     renfer
    -0.53
     ouvre
    -0.52
     réuss
    -0.52
    POSITIVE LOGITS
     weekend
    1.42
    weekend
    1.31
     Weekend
    1.25
    Weekend
    1.24
     WEEKEND
    1.16
     weekends
    1.15
     Wochenende
    0.78
     Saturday
    0.77
     keramik
    0.73
    Saturday
    0.73
    Activations Density 0.034%

    No Known Activations