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. 10146
    Prev
    Next
    INDEX
    Explanations

    references to glass, such as glass walkways and glassblowing

    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
    896
    +0.16
    0.6%
    1624
    +0.16
    0.6%
    1926
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    896
    +0.16
    0.02
    1624
    +0.16
    0.03
    899
    +0.13
    0.02
    Negative Logits
    ArgumentParser
    -0.52
    IsNotNull
    -0.50
    ExtendWith
    -0.50
     Segen
    -0.49
    XmlEnum
    -0.48
     تضيفلها
    -0.48
    PostExecute
    -0.47
    daction
    -0.47
    Ứng
    -0.46
    PreExecute
    -0.45
    POSITIVE LOGITS
     glass
    1.39
    glass
    1.34
     Glass
    1.32
    Glass
    1.31
     GLASS
    1.18
     glasses
    1.08
    GLASS
    1.08
     glas
    1.03
    glas
    0.95
    glasses
    0.89
    Activations Density 0.082%

    No Known Activations