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. 15710
    Prev
    Next
    INDEX
    Explanations

    quotations within text

    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
    2019
    +0.28
    0.9%
    381
    +0.13
    0.4%
    304
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.28
    0.07
    2019
    +0.13
    0.07
    545
    +0.12
    0.05
    Negative Logits
     me
    -0.59
     na
    -0.54
     or
    -0.53
     per
    -0.53
    ,
    -0.52
    suporte
    -0.51
     so
    -0.51
     song
    -0.51
    Welke
    -0.51
    Jakie
    -0.50
    POSITIVE LOGITS
     jaya
    1.29
     antik
    1.04
     maksi
    1.03
     katun
    1.01
     kemer
    1.00
     kafe
    0.98
     panik
    0.97
    timately
    0.97
     bandung
    0.97
    tempts
    0.97
    Activations Density 0.267%

    No Known Activations