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. 768
    Prev
    Next
    INDEX
    Explanations

    text related to the concept of sacrifice, particularly in personal relationships or moral contexts

    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
    899
    +0.14
    0.5%
    196
    +0.11
    0.4%
    11
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    899
    +0.14
    0.03
    11
    +0.11
    0.02
    1876
    +0.11
    0.02
    Negative Logits
     revan
    -0.85
     Sinal
    -0.80
     Cuer
    -0.77
     colombia
    -0.77
     EEU
    -0.75
     Doña
    -0.74
     Epif
    -0.74
     concier
    -0.74
     Monto
    -0.74
     philanth
    -0.70
    POSITIVE LOGITS
     sacrifice
    1.14
     Sacrifice
    1.06
    sacrifice
    1.02
     sacrificed
    0.99
     sacrifices
    0.99
     sacrificing
    0.98
     compromise
    0.93
    sacrific
    0.87
     compromising
    0.80
     sacrificio
    0.77
    Activations Density 0.110%

    No Known Activations