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. 15130
    Prev
    Next
    INDEX
    Explanations

    descriptions of places, events, and interactions within a community setting

    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
    1013
    +0.14
    0.4%
    1467
    +0.11
    0.3%
    1870
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1467
    +0.14
    0.06
    284
    +0.11
    0.08
    2044
    +0.09
    0.08
    Negative Logits
     uhr
    -1.04
     Wikiquote
    -0.98
     BIBSYS
    -0.98
     Sén
    -0.97
     meis
    -0.95
     NKC
    -0.95
     valla
    -0.95
     quoc
    -0.95
     RSSSF
    -0.94
     Liban
    -0.94
    POSITIVE LOGITS
     épreuves
    0.66
     navires
    0.64
     or
    0.63
     somewhere
    0.62
     from
    0.59
     apiece
    0.58
     someplace
    0.57
     jambes
    0.57
     McLaugh
    0.57
     journées
    0.56
    Activations Density 0.538%

    No Known Activations