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. 1863
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating future possibility or necessity

    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
    +0.19
    0.8%
    900
    +0.13
    0.5%
    1222
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.19
    0.06
    1108
    +0.13
    0.06
    1243
    +0.10
    0.05
    Negative Logits
    <bos>
    -1.95
     intersper
    -1.02
     shenan
    -0.78
     encomp
    -0.78
     McInt
    -0.77
     reluct
    -0.75
     attemp
    -0.74
     depic
    -0.72
     crou
    -0.72
     inconce
    -0.70
    POSITIVE LOGITS
    ">...
    0.78
    ">/
    0.75
    :"-
    0.70
    ">“
    0.67
    ]**
    0.65
    limsy
    0.65
    ]--;
    0.64
    Sklici
    0.64
     Może
    0.63
     bambina
    0.62
    Activations Density 0.348%

    No Known Activations