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. 15981
    Prev
    Next
    INDEX
    Explanations

    botanical descriptions, particularly those related to rare plants and their characteristics

    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
    555
    +0.16
    0.6%
    1624
    +0.14
    0.5%
    25
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1624
    +0.16
    0.03
    605
    +0.14
    0.01
    1008
    +0.13
    0.02
    Negative Logits
     Pemberton
    -0.50
    нутрен
    -0.48
    sergio
    -0.46
    können
    -0.45
    iç
    -0.45
    pisah
    -0.45
     Realt
    -0.45
    Transcrip
    -0.43
    pS
    -0.43
    $-.
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.75
    +:+
    0.58
     ostavi
    0.56
    __;
    0.55
    expandindo
    0.55
    Personendaten
    0.55
     volon
    0.54
    EMPO
    0.53
    astricht
    0.51
    Carriera
    0.51
    Activations Density 0.141%

    No Known Activations