© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12723
    Prev
    Next
    INDEX
    Explanations

    references to religious beliefs and doctrines centered around concepts of sin, judgment, and God's will

    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
    855
    +0.09
    0.2%
    559
    +0.07
    0.2%
    478
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    855
    +0.09
    0.03
    1901
    +0.07
    0.02
    134
    +0.07
    0.03
    Negative Logits
     encomp
    -1.15
     depic
    -1.06
     umo
    -0.99
     attemp
    -0.99
     katun
    -0.98
     impra
    -0.97
     increa
    -0.95
     susun
    -0.95
     purcha
    -0.95
     maneu
    -0.93
    POSITIVE LOGITS
     Himself
    0.64
    ніципалі
    0.60
    bitat
    0.56
    elemField
    0.54
    Népesség
    0.53
    vânt
    0.53
    略歴
    0.50
     himself
    0.50
     învă
    0.48
    pfung
    0.47
    Activations Density 0.161%

    No Known Activations