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. 6714
    Prev
    Next
    INDEX
    Explanations

    the mention of the name "Adrian" in various contexts

    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
    1404
    +0.16
    0.8%
    1994
    +0.15
    0.8%
    597
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.16
    0.04
    1056
    +0.15
    0.03
    227
    +0.15
    0.03
    Negative Logits
    <bos>
    -1.27
    
    
    -0.66
     disambiguazione
    -0.63
     enable
    -0.60
    jooq
    -0.60
    hastly
    -0.57
    iestety
    -0.56
    #
    -0.56
     verwijzen
    -0.56
    حياتها
    -0.56
    POSITIVE LOGITS
     fta
    1.33
     dora
    1.24
     »>
    1.24
     „,
    1.20
     lara
    1.20
     squa
    1.19
     ftu
    1.19
     fte
    1.18
     wherea
    1.17
     nico
    1.17
    Activations Density 0.159%

    No Known Activations