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. 15038
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software components or coding

    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
    893
    +0.13
    0.5%
    395
    +0.12
    0.5%
    122
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    395
    +0.13
    0.02
    893
    +0.12
    0.02
    325
    +0.12
    0.02
    Negative Logits
     Darío
    -0.90
     alberto
    -0.82
     philanth
    -0.80
     accla
    -0.79
     indestru
    -0.77
     jorge
    -0.77
     sergio
    -0.75
     Mónica
    -0.74
     disgra
    -0.72
     unspeak
    -0.72
    POSITIVE LOGITS
     component
    1.40
     Component
    1.33
     components
    1.31
    component
    1.28
     Components
    1.24
    Component
    1.24
    components
    1.17
    COMPONENT
    1.07
    Components
    1.05
     componente
    1.00
    Activations Density 0.053%

    No Known Activations