© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12551
    Prev
    Next
    INDEX
    Explanations

    verbs related to pursuing careers or missions, particularly in the context of justice and acting, as well as mentions of living in specific locations

    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
    227
    +0.10
    0.3%
    1217
    +0.07
    0.2%
    311
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1217
    +0.10
    0.03
    1002
    +0.07
    0.04
    952
    +0.07
    0.03
    Negative Logits
     impra
    -1.17
     increa
    -1.06
     suscep
    -1.05
     jacques
    -1.01
     indestru
    -0.97
     disreg
    -0.96
     effe
    -0.95
     oleo
    -0.95
     antem
    -0.95
     pollut
    -0.94
    POSITIVE LOGITS
     retirement
    0.71
    Hentet
    0.64
    retirement
    0.59
     BoxFit
    0.59
     freelance
    0.59
    astéroïdes
    0.57
     retired
    0.57
     ISNI
    0.57
    rungsseite
    0.56
     coaching
    0.55
    Activations Density 0.398%

    No Known Activations