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. 1599
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal opinions or evaluations

    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
    674
    +0.09
    0.3%
    604
    +0.08
    0.2%
    47
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    689
    +0.09
    0.04
    390
    +0.08
    0.04
    169
    +0.08
    0.03
    Negative Logits
     antem
    -0.97
     aton
    -0.97
     bandung
    -0.96
     lele
    -0.94
     Minang
    -0.93
     gend
    -0.90
     accla
    -0.90
     depic
    -0.90
     territo
    -0.90
     mef
    -0.89
    POSITIVE LOGITS
     includes
    0.66
     brings
    0.59
     thats
    0.59
     why
    0.58
     makes
    0.58
     reflects
    0.57
     happens
    0.56
     happened
    0.55
     allows
    0.55
     requires
    0.54
    Activations Density 0.138%

    No Known Activations