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. 8349
    Prev
    Next
    INDEX
    Explanations

    references to technological advancements and developments, particularly in the fields of machine learning and cryptocurrency

    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
    453
    +0.18
    0.5%
    198
    +0.11
    0.3%
    715
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.18
    0.07
    453
    +0.11
    0.08
    227
    +0.09
    0.09
    Negative Logits
     ftu
    -1.73
     »>
    -1.53
     ftre
    -1.51
     thut
    -1.50
     fta
    -1.49
     tranf
    -1.48
     fup
    -1.46
     perfon
    -1.45
    «<
    -1.44
     fays
    -1.43
    POSITIVE LOGITS
     worldwide
    0.61
     popular
    0.55
     widely
    0.54
     famous
    0.53
     highly
    0.52
     trillion
    0.52
     world
    0.50
     global
    0.49
     immensely
    0.49
    bonucleic
    0.49
    Activations Density 1.107%

    No Known Activations