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. 2292
    Prev
    Next
    INDEX
    Explanations

    phrases related to resource allocation and time management

    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
    1013
    +0.08
    0.2%
    2006
    +0.07
    0.2%
    1298
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1298
    +0.08
    0.04
    1171
    +0.07
    0.04
    1283
    +0.07
    0.04
    Negative Logits
     Juf
    -1.44
     meis
    -1.25
     quoc
    -1.23
     doman
    -1.21
     fta
    -1.21
     mef
    -1.20
     lele
    -1.19
     dises
    -1.19
     accla
    -1.19
     increa
    -1.19
    POSITIVE LOGITS
     spent
    1.12
     devoted
    1.06
     dedicated
    0.91
     spend
    0.88
    spent
    0.86
     devote
    0.80
     wasted
    0.78
    dedicated
    0.78
     invested
    0.77
     allocated
    0.76
    Activations Density 0.296%

    No Known Activations