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. 1057
    Prev
    Next
    INDEX
    Explanations

    terms related to legal arbitration processes

    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
    1065
    +0.17
    0.8%
    397
    +0.13
    0.7%
    506
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.17
    0.02
    1896
    +0.13
    0.02
    1065
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.37
     intersper
    -0.76
     amass
    -0.76
     encomp
    -0.74
     endow
    -0.71
     gratify
    -0.69
     disbur
    -0.67
     implore
    -0.64
     ascribe
    -0.63
     underval
    -0.63
    POSITIVE LOGITS
     arbitration
    1.12
    Arbit
    1.12
     Arbit
    1.05
     Arbitration
    1.04
     arbit
    1.02
    arbit
    0.96
     arbitrator
    0.92
     arbitrators
    0.83
    putes
    0.72
     arb
    0.70
    Activations Density 0.170%

    No Known Activations