Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13457
    Prev
    Next
    INDEX
    Explanations

    phrases that evoke a complex mix of emotions, such as feeling both sad and happy at the same time, and nostalgia for past generations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1314
    +0.09
    0.3%
    1651
    +0.08
    0.2%
    1013
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1314
    +0.09
    0.04
    1235
    +0.08
    0.03
    1666
    +0.07
    0.03
    Negative Logits
     disagre
    -1.09
     reluct
    -1.08
     depic
    -1.07
     fte
    -1.07
     perfon
    -1.05
     reft
    -1.05
     fup
    -1.03
     greate
    -1.03
     ftu
    -1.03
     thut
    -1.02
    POSITIVE LOGITS
     simultaneously
    1.38
     одновременно
    1.04
     zugleich
    0.99
     gleichzeitig
    0.98
    simult
    0.95
     alike
    0.94
     concurrently
    0.91
     simult
    0.89
     simultaneous
    0.87
     jednocześnie
    0.78
    Activations Density 0.310%

    No Known Activations