Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2774
    Prev
    Next
    INDEX
    Explanations

    quotations starting with the word "that."

    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
    161
    +0.18
    0.7%
    506
    +0.14
    0.5%
    1350
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.18
    0.05
    1023
    +0.14
    0.04
    506
    +0.13
    0.03
    Negative Logits
     AppBundle
    -0.61
     gius
    -0.60
     Viene
    -0.59
     chied
    -0.59
     Più
    -0.58
     sappi
    -0.57
     joi
    -0.57
     perfet
    -0.57
     conclud
    -0.57
    Lma
    -0.56
    POSITIVE LOGITS
     they
    0.67
     that
    0.67
     there
    0.59
     THAT
    0.58
    that
    0.56
     it
    0.55
     everybody
    0.52
     That
    0.52
     we
    0.51
     nobody
    0.51
    Activations Density 0.166%

    No Known Activations