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. 15830
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific legal program or policy, particularly focusing on the Deferred Action for Childhood Arrivals (DACA)

    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
    1842
    +0.12
    0.4%
    1553
    +0.11
    0.3%
    1597
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.12
    0.06
    1597
    +0.11
    0.03
    1105
    +0.09
    0.04
    Negative Logits
     pimiento
    -0.79
     DIOS
    -0.71
     haer
    -0.69
     saluti
    -0.68
     jamón
    -0.68
     PREFACE
    -0.67
     applau
    -0.66
     churrasco
    -0.65
     rir
    -0.64
     anton
    -0.64
    POSITIVE LOGITS
     immigrants
    0.79
     immigrant
    0.75
     immigration
    0.73
     deportation
    0.66
     Immigration
    0.64
     undocumented
    0.61
     migrant
    0.60
     migrants
    0.59
     deported
    0.59
     immig
    0.58
    Activations Density 0.338%

    No Known Activations