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. 1347
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and self-improvement

    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
    604
    +0.14
    0.4%
    1531
    +0.09
    0.3%
    1698
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1531
    +0.14
    0.04
    1580
    +0.09
    0.03
    2026
    +0.08
    0.03
    Negative Logits
     alkoh
    -1.04
     uhr
    -1.00
     kompati
    -0.99
     maksi
    -0.97
     keramik
    -0.96
     lele
    -0.93
     Kategor
    -0.93
    <bos>
    -0.93
     lemp
    -0.93
     antik
    -0.91
    POSITIVE LOGITS
     unnecessary
    0.69
     harmful
    0.62
     unhealthy
    0.62
     wastes
    0.61
     unhelpful
    0.59
     wasted
    0.58
     pointless
    0.58
     ineffective
    0.57
     detrimental
    0.57
     unnecessarily
    0.56
    Activations Density 0.387%

    No Known Activations