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. 13639
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    674
    +0.27
    0.9%
    1153
    +0.05
    0.2%
    269
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    -0.27
    0.00
    0
    -0.05
    0.00
    1
    -0.05
    0.00
    Negative Logits
     reluct
    -4.76
     shenan
    -4.70
     unspeak
    -4.57
     disagre
    -4.47
     impra
    -4.37
     depic
    -4.29
     increa
    -4.29
     apprehen
    -4.26
     encomp
    -4.21
     maneu
    -4.11
    POSITIVE LOGITS
    <bos>
    8.74
     Walkover
    2.39
     Himo
    2.38
     Paglinawan
    2.29
    GEBURTSDATUM
    2.17
     himo
    2.15
     betweenstory
    2.11
     Shetterly
    2.07
    脚注の使い方
    2.04
     '\\;'
    2.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.