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. 1132
    Prev
    Next
    INDEX
    Explanations

    mentions of NPR or related terms

    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
    874
    +0.15
    0.7%
    196
    +0.14
    0.7%
    1265
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.15
    0.00
    227
    +0.14
    0.03
    1101
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.30
    SourceChecksum
    -0.75
    contentLoaded
    -0.67
    HasIndex
    -0.66
    bootstrapcdn
    -0.65
    styleType
    -0.65
    LayoutStyle
    -0.62
    StructEnd
    -0.61
    esModule
    -0.60
    IsContent
    -0.58
    POSITIVE LOGITS
     NPR
    1.37
    NPR
    1.25
     snoopy
    0.88
     Karang
    0.84
     eiffel
    0.80
     Khart
    0.80
     Châ
    0.79
     Præ
    0.79
     bordeaux
    0.79
     kraken
    0.79
    Activations Density 0.130%

    No Known Activations