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. 536
    Prev
    Next
    INDEX
    Explanations

    phrases related to UFO sightings and conspiracy theories

    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
    468
    +0.07
    0.2%
    295
    +0.07
    0.2%
    1617
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.07
    0.04
    564
    +0.07
    0.05
    295
    +0.06
    0.02
    Negative Logits
     reluct
    -2.25
     increa
    -2.16
     impra
    -2.11
     inev
    -2.06
     affor
    -2.06
     disagre
    -2.03
     encomp
    -1.96
     maneu
    -1.96
     unden
    -1.94
     depic
    -1.93
    POSITIVE LOGITS
     mere
    0.64
    MemoryWarning
    0.61
    ModelSerializer
    0.61
    UnitTesting
    0.60
    ruptedException
    0.60
    הס
    0.60
     հղումներ
    0.60
    StructEnd
    0.60
     normal
    0.60
    הע
    0.59
    Activations Density 0.430%

    No Known Activations