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. 1146
    Prev
    Next
    INDEX
    Explanations

    expressions related to future possibilities or hopes

    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
    +0.20
    0.8%
    1671
    +0.12
    0.5%
    1271
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1671
    +0.20
    0.03
    1856
    +0.12
    0.03
    1406
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.13
    /***
    
    -0.64
    <>
    
    -0.59
    //@
    -0.58
    diff
    -0.57
    bardziej
    -0.52
    ///**
    -0.51
    aff
    -0.51
    Abril
    -0.51
    Legături
    -0.50
    POSITIVE LOGITS
     kram
    1.08
     jaya
    1.00
     wien
    1.00
     tyme
    0.99
    requently
    0.98
     unlaw
    0.98
     lele
    0.98
     frankfurt
    0.97
     utop
    0.96
     ohr
    0.96
    Activations Density 0.136%

    No Known Activations