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. 15028
    Prev
    Next
    INDEX
    Explanations

    famous historical figures and events

    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
    964
    +0.31
    1.2%
    184
    +0.24
    0.9%
    1842
    +0.22
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.31
    0.04
    964
    +0.24
    0.05
    1842
    +0.22
    0.05
    Negative Logits
    <bos>
    -0.85
     palio
    -0.78
     abbra
    -0.71
     ristor
    -0.71
     lapto
    -0.69
     merav
    -0.68
     vola
    -0.65
     fumo
    -0.64
     lancia
    -0.64
     chicco
    -0.64
    POSITIVE LOGITS
     indor
    0.56
    ChildScrollView
    0.54
     Lieut
    0.51
    TimeoutException
    0.48
     Shakspeare
    0.45
    Rgds
    0.45
     thereupon
    0.44
    parsedMessage
    0.44
    SneakyThrows
    0.43
    FormatException
    0.43
    Activations Density 0.462%

    No Known Activations