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. 1794
    Prev
    Next
    INDEX
    Explanations

    references to a specific location or venue, particularly an arena

    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
    +0.19
    1.1%
    32
    +0.12
    0.7%
    501
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1178
    +0.19
    0.02
    501
    +0.12
    0.01
    1034
    +0.12
    0.01
    Negative Logits
    <bos>
    -2.30
    //---
    -0.64
     endow
    -0.59
     deepen
    -0.59
     rejoin
    -0.59
     cooperated
    -0.58
     preside
    -0.56
     straighten
    -0.55
     inaugurate
    -0.54
     unify
    -0.54
    POSITIVE LOGITS
     arena
    1.34
     Arena
    1.27
    Arena
    1.19
     arenas
    1.08
    arena
    1.08
     swarovski
    0.98
     Pièces
    0.97
     dégust
    0.91
     ecru
    0.89
     Arenas
    0.89
    Activations Density 0.047%

    No Known Activations