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. 953
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and entities, particularly in a news context

    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
    +0.34
    1.3%
    1177
    +0.11
    0.4%
    752
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1177
    +0.34
    0.01
    1362
    +0.11
    0.05
    1430
    +0.08
    0.04
    Negative Logits
    <bos>
    -1.85
     !...
    -1.42
     :)))
    -1.28
     fup
    -1.24
     indestru
    -1.22
     ciao
    -1.22
     fign
    -1.21
     chande
    -1.20
     encomp
    -1.20
     igno
    -1.19
    POSITIVE LOGITS
    Sklici
    0.58
    corollary
    0.56
    objPHPExcel
    0.55
    Nasc
    0.55
    Muerte
    0.55
    MouseAdapter
    0.55
    rcParams
    0.54
    yticks
    0.54
    splitContainer
    0.53
    pylab
    0.53
    Activations Density 0.811%

    No Known Activations