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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14456
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emphasis or clarification in a conversation

    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
    872
    +0.13
    0.4%
    674
    +0.11
    0.3%
    1836
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.13
    0.05
    1791
    +0.11
    0.03
    1433
    +0.07
    0.03
    Negative Logits
     accla
    -1.33
     unlaw
    -1.33
     reluct
    -1.31
     depic
    -1.29
     increa
    -1.27
     antem
    -1.26
     embra
    -1.23
     attemp
    -1.23
     laun
    -1.22
     Middles
    -1.21
    POSITIVE LOGITS
     meaning
    0.89
     means
    0.88
     refers
    0.87
     refer
    0.79
     mean
    0.77
    meaning
    0.75
    means
    0.74
     defined
    0.73
     implies
    0.73
     necesar
    0.72
    Activations Density 0.288%

    No Known Activations