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. 15757
    Prev
    Next
    INDEX
    Explanations

    terms related to changes, impacts, and issues in various fields such as sports, economics, law, and the environment

    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
    581
    +0.10
    0.3%
    1173
    +0.08
    0.2%
    1042
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    581
    +0.10
    0.06
    1138
    +0.08
    0.04
    1483
    +0.07
    0.05
    Negative Logits
     elek
    -0.91
     alkoh
    -0.91
     ananas
    -0.91
     hek
    -0.88
     kram
    -0.88
     stoff
    -0.86
     lü
    -0.83
     plak
    -0.81
     kug
    -0.79
     augus
    -0.78
    POSITIVE LOGITS
     unve
    0.65
    czegóły
    0.63
     déclarations
    0.63
    jątk
    0.59
     is
    0.58
     was
    0.58
    prägt
    0.57
     involves
    0.55
     seems
    0.55
    дравству
    0.55
    Activations Density 0.327%

    No Known Activations