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. 13602
    Prev
    Next
    INDEX
    Explanations

    references to education and examination-related context

    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
    50
    +0.43
    1.8%
    674
    +0.27
    1.1%
    1177
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.43
    0.08
    1177
    +0.27
    0.04
    227
    +0.11
    0.08
    Negative Logits
    Ant
    -0.71
     em
    -0.68
    Tras
    -0.67
    "
    -0.67
    Pat
    -0.67
    Por
    -0.66
    Em
    -0.66
     "
    -0.66
    Rub
    -0.66
    Mas
    -0.66
    POSITIVE LOGITS
     inev
    2.77
     increa
    2.76
     inappro
    2.74
     impra
    2.71
     encomp
    2.70
     desir
    2.68
     indestru
    2.67
     effe
    2.67
     depic
    2.66
     ftu
    2.66
    Activations Density 0.754%

    No Known Activations