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. 13588
    Prev
    Next
    INDEX
    Explanations

    specific references to time periods and milestones, such as years and career stages

    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
    1856
    +0.12
    0.3%
    1962
    +0.09
    0.3%
    175
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1856
    +0.12
    0.07
    1962
    +0.09
    0.06
    1379
    +0.07
    0.04
    Negative Logits
     increa
    -1.66
     squa
    -1.65
     fta
    -1.65
     impra
    -1.61
     chery
    -1.61
     inev
    -1.59
     encomp
    -1.58
     affor
    -1.55
     effe
    -1.55
     lyon
    -1.54
    POSITIVE LOGITS
     iprot
    0.71
     gradually
    0.68
    JspWriter
    0.67
     colspan
    0.64
     pageContext
    0.63
    ScopeManager
    0.61
     numerous
    0.61
     Paglinawan
    0.61
    MathML
    0.60
    ValueStyle
    0.60
    Activations Density 0.463%

    No Known Activations