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. 6755
    Prev
    Next
    INDEX
    Explanations

    terminology related to negotiations and settlements

    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
    1842
    +0.25
    1.0%
    50
    +0.21
    0.8%
    604
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.25
    0.01
    1904
    +0.21
    0.07
    1290
    +0.15
    0.07
    Negative Logits
    <bos>
    -3.06
     intersper
    -1.92
     encomp
    -1.42
     reluct
    -1.42
     reconno
    -1.38
     inconce
    -1.36
     shenan
    -1.34
     indoc
    -1.33
     disambigu
    -1.32
     overcrow
    -1.32
    POSITIVE LOGITS
     jati
    0.87
     tantum
    0.82
     potest
    0.79
     demokra
    0.77
     asfal
    0.76
     hect
    0.76
     mikrofon
    0.75
     nikah
    0.75
     hunde
    0.75
     blanda
    0.73
    Activations Density 1.132%

    No Known Activations