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. 8197
    Prev
    Next
    INDEX
    Explanations

    texts describing excellence or things related to excellence

    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
    478
    +0.16
    0.6%
    994
    +0.13
    0.5%
    197
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.16
    0.03
    1512
    +0.13
    0.03
    1145
    +0.12
    0.03
    Negative Logits
     McLaugh
    -0.65
     indestru
    -0.64
     unwarran
    -0.61
     unspeak
    -0.60
     compréhen
    -0.59
     McF
    -0.57
     impelled
    -0.56
     inconce
    -0.55
     reclamar
    -0.55
     Vaugh
    -0.54
    POSITIVE LOGITS
    excellent
    0.84
    cellent
    0.80
     excellent
    0.79
     Excellent
    0.78
     excellence
    0.77
     EXCELL
    0.77
     tille
    0.75
    Excellent
    0.75
     tyn
    0.72
     corpi
    0.72
    Activations Density 0.112%

    No Known Activations