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. 647
    Prev
    Next
    INDEX
    Explanations

    financial impacts and costs associated with projects or programs

    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
    +0.28
    1.1%
    1013
    +0.14
    0.5%
    1042
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1965
    +0.28
    0.05
    615
    +0.14
    0.06
    1935
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.33
     disbur
    -0.74
     handels
    -0.67
     harmonize
    -0.66
    /**
    -0.63
    
    
    -0.63
     inaugurate
    -0.60
     handel
    -0.58
     reinstate
    -0.58
     exemplify
    -0.58
    POSITIVE LOGITS
     churrasco
    1.12
     paradiso
    1.12
     bandung
    1.11
     lusso
    1.01
     dégust
    1.00
     lavable
    0.99
     nutella
    0.97
     pandan
    0.96
     ristor
    0.96
     pimiento
    0.96
    Activations Density 0.493%

    No Known Activations