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. 1151
    Prev
    Next
    INDEX
    Explanations

    concepts related to desire and existential thought

    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
    +0.20
    0.8%
    50
    +0.15
    0.6%
    394
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.20
    0.05
    1842
    +0.15
    0.04
    455
    +0.12
    0.05
    Negative Logits
    <bos>
    -2.83
    Autoritní
    -0.99
    脚注の使い方
    -0.91
    Atsauces
    -0.90
     nakalista
    -0.85
    Билгалдахарш
    -0.84
     المعيارى
    -0.83
    طلحات
    -0.82
    displayquote
    -0.81
    UnitTesting
    -0.80
    POSITIVE LOGITS
     affor
    2.09
     stockholm
    2.05
     bandung
    2.03
     increa
    2.02
     🤣🤣
    1.95
     strick
    1.93
     impra
    1.91
     disagre
    1.90
     wien
    1.90
     jaya
    1.89
    Activations Density 0.702%

    No Known Activations