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. 15829
    Prev
    Next
    INDEX
    Explanations

    phrases related to gaining something, whether it's ownership, entry, seating, or power

    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
    1562
    +0.12
    0.4%
    1265
    +0.12
    0.4%
    537
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1562
    +0.12
    0.03
    537
    +0.12
    0.02
    489
    +0.11
    0.02
    Negative Logits
     للمعارف
    -0.56
    formik
    -0.48
    UniformLocation
    -0.47
     Murphy
    -0.46
     Ar
    -0.44
     Nolan
    -0.43
     Ако
    -0.43
     Fro
    -0.43
    HasForeignKey
    -0.42
     Bristol
    -0.42
    POSITIVE LOGITS
     GAIN
    1.21
     gain
    1.11
     swarovski
    1.10
     nutella
    1.08
    gain
    1.08
     Gain
    1.07
     sappi
    1.06
    gains
    1.03
     Gains
    1.00
     gains
    1.00
    Activations Density 0.070%

    No Known Activations