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. 1527
    Prev
    Next
    INDEX
    Explanations

    ways that things diminish or lose intensity over time

    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
    690
    +0.10
    0.3%
    1896
    +0.10
    0.3%
    1443
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.10
    0.04
    1135
    +0.10
    0.03
    1896
    +0.10
    0.02
    Negative Logits
     shenan
    -1.72
     reluct
    -1.63
     depic
    -1.59
     encomp
    -1.54
     impra
    -1.53
     accla
    -1.50
     resear
    -1.49
     guarante
    -1.49
     snoopy
    -1.48
     increa
    -1.47
    POSITIVE LOGITS
     fade
    0.84
    fade
    0.80
     decay
    0.79
     fading
    0.75
    decay
    0.74
    Fade
    0.69
     away
    0.66
     faded
    0.64
    degenerative
    0.61
    oflavin
    0.59
    Activations Density 0.187%

    No Known Activations