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. 1845
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation marks indicating pauses in sentences

    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
    +0.26
    1.4%
    2019
    +0.14
    0.7%
    1045
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.26
    0.17
    2019
    +0.14
    0.16
    2034
    +0.12
    0.15
    Negative Logits
    <bos>
    -2.67
    anță
    -0.91
     analyze
    -0.80
    ാൻ
    -0.79
     finalize
    -0.77
    ⓧ
    -0.77
     honor
    -0.76
     realize
    -0.76
     materialize
    -0.75
     organize
    -0.74
    POSITIVE LOGITS
     Juf
    1.19
     McLaugh
    1.13
     Gorb
    1.13
     McInt
    1.06
     véhic
    1.04
     malheure
    1.02
     Rine
    1.01
     soulign
    1.00
     désol
    0.98
     eorum
    0.98
    Activations Density 1.494%

    No Known Activations