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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 911
    Prev
    Next
    INDEX
    Explanations

    indications of negation and uncertainty in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.22
    0.8%
    468
    +0.12
    0.4%
    47
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.22
    0.04
    1292
    +0.12
    0.04
    972
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.28
     intersper
    -1.09
     disambigu
    -0.94
     intermitt
    -0.86
     unsus
    -0.85
     intrigu
    -0.84
     endow
    -0.83
     unspeak
    -0.82
     ineffec
    -0.81
     guil
    -0.81
    POSITIVE LOGITS
     signora
    1.05
     sorella
    1.03
     vacanza
    0.98
     paradiso
    0.93
     preghi
    0.92
     sfera
    0.90
     Muhamma
    0.89
     dott
    0.89
     muna
    0.87
    ">/
    0.86
    Activations Density 0.325%

    No Known Activations