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. 1422
    Prev
    Next
    INDEX
    Explanations

    Biblical references and theological concepts

    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
    1741
    +0.11
    0.3%
    1380
    +0.11
    0.3%
    924
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1786
    +0.11
    0.01
    499
    +0.11
    0.02
    1612
    +0.10
    0.01
    Negative Logits
     Shakspeare
    -0.91
     nutella
    -0.90
     swarovski
    -0.90
     fluo
    -0.84
     Abbé
    -0.84
     tupperware
    -0.81
     murano
    -0.80
     ingrat
    -0.77
     Shaksp
    -0.77
     disgra
    -0.77
    POSITIVE LOGITS
    iastes
    0.59
    <bos>
    0.58
     Kapitel
    0.52
     Furcht
    0.52
    PhysRevD
    0.51
     AttributeSet
    0.51
    lossians
    0.50
    verifyException
    0.49
    BeginContext
    0.48
     NSCoder
    0.47
    Activations Density 0.066%

    No Known Activations