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. 3000
    Prev
    Next
    INDEX
    Explanations

    mentions of job titles and roles within various organizations

    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
    227
    +0.17
    0.5%
    198
    +0.12
    0.3%
    1842
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.17
    0.04
    16
    +0.12
    0.06
    198
    +0.12
    0.04
    Negative Logits
     reft
    -0.77
     tranf
    -0.75
     ACKNOWLEDGMENTS
    -0.70
     nutella
    -0.67
     :—
    -0.65
    hastly
    -0.64
     lefs
    -0.63
     unce
    -0.62
     thut
    -0.61
     foon
    -0.61
    POSITIVE LOGITS
     clients
    0.79
     Áng
    0.76
     Barcelone
    0.65
     Berlín
    0.65
     Jardín
    0.63
     Vaticano
    0.60
    clients
    0.60
     Bahía
    0.60
     Jérusalem
    0.59
     ModelExpression
    0.59
    Activations Density 0.412%

    No Known Activations