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. 14954
    Prev
    Next
    INDEX
    Explanations

    phrases related to sums, values, and calculations

    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
    680
    +0.14
    0.6%
    1705
    +0.12
    0.5%
    1637
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1637
    +0.14
    0.02
    537
    +0.12
    0.02
    849
    +0.11
    0.02
    Negative Logits
     Deh
    -0.52
     Bekasi
    -0.48
    ჟ
    -0.48
    mybatisplus
    -0.45
     Gä
    -0.44
    marginHorizontal
    -0.42
     Macquarie
    -0.42
    FlatStyle
    -0.42
     McA
    -0.41
    Ще
    -0.40
    POSITIVE LOGITS
     SUM
    1.05
     Sum
    1.02
    sum
    0.96
    Sum
    0.96
    SUM
    0.94
     sum
    0.94
     sums
    0.93
    sums
    0.92
    Summit
    0.88
     summit
    0.84
    Activations Density 0.107%

    No Known Activations