© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13031
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulations, exceptions, and standards in business and government

    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
    674
    +0.08
    0.2%
    1700
    +0.07
    0.2%
    706
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1700
    +0.08
    0.02
    580
    +0.07
    0.02
    584
    +0.07
    0.02
    Negative Logits
     reluct
    -1.40
     disagre
    -1.38
     encomp
    -1.34
     depic
    -1.33
     unspeak
    -1.31
     indestru
    -1.29
     affor
    -1.29
     sophistic
    -1.28
     impra
    -1.26
     pamph
    -1.25
    POSITIVE LOGITS
     exception
    0.98
     EconPapers
    0.86
     exceptions
    0.85
     Exception
    0.84
     norm
    0.81
     norma
    0.78
     anormal
    0.77
    Exception
    0.74
     kast
    0.69
     excepción
    0.69
    Activations Density 0.166%

    No Known Activations