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. 13496
    Prev
    Next
    INDEX
    Explanations

    positive expressions referring to commitment, drive, and love

    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
    50
    +0.10
    0.3%
    1823
    +0.10
    0.3%
    227
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.10
    0.06
    1823
    +0.10
    0.03
    260
    +0.09
    0.03
    Negative Logits
     kasa
    -1.50
     umo
    -1.48
     lele
    -1.45
     jaya
    -1.43
     levis
    -1.42
     hina
    -1.41
     mef
    -1.38
     lyon
    -1.38
     kug
    -1.37
     makro
    -1.36
    POSITIVE LOGITS
    <bos>
    0.83
     himself
    0.74
     always
    0.64
     proud
    0.63
     loves
    0.63
     feels
    0.62
     believes
    0.62
     enjoys
    0.61
     prefers
    0.59
     still
    0.58
    Activations Density 0.345%

    No Known Activations