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. 8284
    Prev
    Next
    INDEX
    Explanations

    information related to statistics and data analysis

    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
    1967
    +0.33
    1.2%
    1343
    +0.23
    0.8%
    674
    +0.19
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1967
    +0.33
    0.05
    1804
    +0.23
    0.06
    2011
    +0.19
    0.04
    Negative Logits
    ,
    -0.84
     that
    -0.79
     a
    -0.78
    .
    -0.77
     and
    -0.75
     for
    -0.75
     or
    -0.74
     so
    -0.74
     which
    -0.74
     as
    -0.73
    POSITIVE LOGITS
     Ottobre
    1.79
     utop
    1.73
     incess
    1.71
     alkoh
    1.68
     Giugno
    1.63
     marte
    1.63
     Settembre
    1.62
     solidar
    1.61
     ordina
    1.61
     Luglio
    1.60
    Activations Density 0.240%

    No Known Activations