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. 6-RES-JB
    6. 8212
    Prev
    Next
    INDEX
    Explanations

    non-standard or alternative words related to the word 'monolithic'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1065
    +0.15
    0.9%
    1376
    +0.14
    0.8%
    1472
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1065
    +0.15
    0.04
    1376
    +0.14
    0.03
    144
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.44
     дописавши
    -0.71
     symbolize
    -0.67
    HasColumnType
    -0.66
     deepen
    -0.61
     collaborate
    -0.61
    <?
    -0.60
     defray
    -0.60
    /*
    -0.60
     regulate
    -0.59
    POSITIVE LOGITS
     Mon
    1.41
     Manufact
    1.29
     MON
    1.28
    Mon
    1.27
     délib
    1.25
     véhic
    1.24
     MONO
    1.22
     monaco
    1.21
     mon
    1.21
     catég
    1.18
    Activations Density 0.148%

    No Known Activations