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. 1859
    Prev
    Next
    INDEX
    Explanations

    concepts related to abstract ideas and their implications 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
    50
    +0.21
    0.9%
    1265
    +0.13
    0.5%
    1870
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.21
    0.08
    990
    +0.13
    0.08
    1870
    +0.12
    0.06
    Negative Logits
    <bos>
    -2.52
    ⓧ
    -0.93
    <?
    -0.87
    
    
    -0.79
    lateinit
    -0.79
    /**
    -0.79
     négociations
    -0.78
    Vegeu
    -0.74
     procédures
    -0.72
     bénéfices
    -0.70
    POSITIVE LOGITS
     levis
    1.49
     unce
    1.48
     paradiso
    1.43
     snoopy
    1.42
     jaya
    1.42
     wien
    1.41
     fter
    1.37
     maroc
    1.36
     milf
    1.36
     affor
    1.34
    Activations Density 0.766%

    No Known Activations