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. 15896
    Prev
    Next
    INDEX
    Explanations

    instances of ownership or possession

    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
    544
    +0.18
    0.6%
    1810
    +0.17
    0.6%
    596
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1810
    +0.18
    0.04
    544
    +0.17
    0.04
    1034
    +0.15
    0.03
    Negative Logits
     revan
    -0.53
     ert
    -0.53
     effe
    -0.52
     pira
    -0.52
     campes
    -0.51
    Allister
    -0.51
     tamb
    -0.50
     cyr
    -0.50
     isabel
    -0.50
     Lauter
    -0.50
    POSITIVE LOGITS
     ownership
    1.06
     Ownership
    1.04
     owned
    1.04
    ownership
    0.96
     owning
    0.96
    owned
    0.95
     Owned
    0.95
     owns
    0.91
    Ownership
    0.90
    owning
    0.89
    Activations Density 0.071%

    No Known Activations