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. 8461
    Prev
    Next
    INDEX
    Explanations

    references to software development practices, specifically focusing on plugins and their maintenance

    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
    227
    +0.12
    0.4%
    876
    +0.11
    0.3%
    1257
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1257
    +0.12
    0.04
    194
    +0.11
    0.02
    1636
    +0.09
    0.02
    Negative Logits
    RESUMEN
    -0.68
    XtraReports
    -0.64
     Paglinawan
    -0.63
    awtextra
    -0.59
    Trayectoria
    -0.58
    ={()=>
    -0.58
    igrette
    -0.57
    ActionResult
    -0.56
    Galería
    -0.56
    piram
    -0.55
    POSITIVE LOGITS
     maneu
    1.25
     affor
    1.19
     increa
    1.19
     scrat
    1.17
     encomp
    1.13
     exciter
    1.13
     contribut
    1.13
     tupperware
    1.12
     hairc
    1.11
     lamborghini
    1.10
    Activations Density 0.543%

    No Known Activations