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. 2816
    Prev
    Next
    INDEX
    Explanations

    dash-separated phrases or quotes

    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
    1350
    +0.16
    0.6%
    381
    +0.14
    0.5%
    2019
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    795
    +0.16
    0.03
    122
    +0.14
    0.04
    214
    +0.13
    0.03
    Negative Logits
    Hvem
    -0.87
    Flere
    -0.81
    Hvorfor
    -0.76
    Hvordan
    -0.75
    ējās
    -0.75
    Hvad
    -0.72
    Ikke
    -0.71
     maintien
    -0.71
    Hvor
    -0.69
    Pozdrawiam
    -0.69
    POSITIVE LOGITS
     magis
    1.05
     kafe
    1.02
     antik
    1.01
     teras
    1.00
     culturali
    0.99
     kram
    0.96
     adal
    0.96
     logis
    0.96
     hant
    0.96
     utop
    0.96
    Activations Density 0.092%

    No Known Activations