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. 6877
    Prev
    Next
    INDEX
    Explanations

    specific instances of family-related situations involving crisis or legal issues

    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
    +0.32
    1.2%
    1177
    +0.14
    0.5%
    1539
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1539
    +0.32
    0.03
    1379
    +0.14
    0.04
    453
    +0.09
    0.06
    Negative Logits
    <bos>
    -2.00
    ⓧ
    -0.72
     itself
    -0.65
    }{||
    -0.63
    /**
    -0.62
    RefNanny
    -0.58
    <?
    -0.56
     himself
    -0.56
    SequentialGroup
    -0.55
    node
    -0.54
    POSITIVE LOGITS
     maneu
    1.69
     accla
    1.63
     reluct
    1.55
     apprehen
    1.55
     shenan
    1.51
     increa
    1.47
     depic
    1.46
     disagre
    1.45
     Juf
    1.41
     inev
    1.39
    Activations Density 1.094%

    No Known Activations