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. 641
    Prev
    Next
    INDEX
    Explanations

    financial figures related to large monetary amounts

    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
    +0.26
    1.3%
    874
    +0.11
    0.5%
    1265
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1935
    +0.26
    0.06
    321
    +0.11
    0.05
    1445
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.82
    ⓧ
    -1.11
    
    
    -1.04
     intersper
    -0.94
    <?
    -0.89
    /**
    -0.85
     endow
    -0.82
     defray
    -0.77
     vanqu
    -0.72
     rouse
    -0.72
    POSITIVE LOGITS
     bandung
    1.35
     kafe
    1.24
     silikon
    1.24
     jawa
    1.18
     ananas
    1.14
     Minang
    1.13
     kela
    1.12
     seksi
    1.11
     Palembang
    1.11
     corrom
    1.10
    Activations Density 0.081%

    No Known Activations