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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 721
    Prev
    Next
    INDEX
    Explanations

    terms related to flexibility and adaptability in work environments

    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
    1870
    +0.14
    0.5%
    1506
    +0.12
    0.4%
    11
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1506
    +0.14
    0.02
    11
    +0.12
    0.02
    1233
    +0.11
    0.02
    Negative Logits
     philanth
    -1.07
     michelin
    -1.06
     embra
    -1.05
     Juf
    -1.03
     unlaw
    -1.01
     reluct
    -0.99
     increa
    -0.99
     disgra
    -0.99
     emphat
    -0.99
     fortn
    -0.98
    POSITIVE LOGITS
     flexible
    1.35
     flexibility
    1.32
     flex
    1.29
    flex
    1.26
    flexible
    1.15
     Flexible
    1.14
    Flexible
    1.14
    Flex
    1.10
     Flex
    1.07
    Flexibility
    1.03
    Activations Density 0.108%

    No Known Activations