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

    Neuronpedia

    Jacobian LensNEW
    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. 14814
    Prev
    Next
    INDEX
    Explanations

    instances of physical actions or interactions between individuals

    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
    1177
    +0.15
    0.5%
    690
    +0.10
    0.3%
    1533
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.15
    0.07
    569
    +0.10
    0.07
    690
    +0.10
    0.04
    Negative Logits
     kosme
    -0.67
     ideolog
    -0.66
     kriminal
    -0.66
    AfterClass
    -0.66
     parlamentar
    -0.64
     praktik
    -0.63
     arit
    -0.61
     mision
    -0.61
     subjek
    -0.61
     klinik
    -0.60
    POSITIVE LOGITS
     disreg
    1.21
     malheureux
    1.18
     jurassic
    1.09
     milf
    1.09
     pixar
    1.08
     malheur
    1.08
     hentai
    1.07
     shenan
    1.03
     POETRY
    1.02
     simpsons
    1.00
    Activations Density 0.481%

    No Known Activations