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. 696
    Prev
    Next
    INDEX
    Explanations

    phrases related to business activities or corporate strategies

    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
    1499
    +0.11
    0.3%
    507
    +0.10
    0.3%
    2000
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1086
    +0.11
    0.06
    1667
    +0.10
    0.06
    1499
    +0.10
    0.08
    Negative Logits
    <bos>
    -0.75
     saurait
    -0.61
     remplace
    -0.55
    أما
    -0.52
     ferait
    -0.52
     jette
    -0.50
    /**
    -0.50
    arrête
    -0.50
     zove
    -0.50
    asteroide
    -0.46
    POSITIVE LOGITS
     Itself
    0.82
     Pyrene
    0.76
     quadr
    0.76
     nephe
    0.74
     itself
    0.74
     embodi
    0.73
     trefoil
    0.73
     logarith
    0.70
     triton
    0.70
     oleo
    0.69
    Activations Density 1.139%

    No Known Activations