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. 1138
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce examples or lists

    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
    +0.35
    1.5%
    1637
    +0.09
    0.4%
    776
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1637
    +0.35
    0.06
    62
    +0.09
    0.05
    561
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.48
    else
    -0.63
     held
    -0.62
     is
    -0.60
    HasColumnType
    -0.59
    @
    -0.59
    <eos>
    -0.58
    IsUnicode
    -0.57
     set
    -0.56
    /***
    -0.56
    POSITIVE LOGITS
     bandung
    1.57
     Minang
    1.43
     lele
    1.40
     jaya
    1.39
     embodi
    1.39
     jawa
    1.37
     maroc
    1.35
     sovere
    1.29
     increa
    1.28
     pymysql
    1.28
    Activations Density 0.336%

    No Known Activations