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. 422
    Prev
    Next
    INDEX
    Explanations

    proper names and titles

    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
    144
    +0.19
    0.7%
    30
    +0.12
    0.5%
    1777
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.19
    0.07
    1778
    +0.12
    0.05
    1335
    +0.12
    0.06
    Negative Logits
    anganronpa
    -0.52
    Ethylbenzene
    -0.47
    Datuak
    -0.45
    énario
    -0.42
    PerformLayout
    -0.41
    InputBorder
    -0.41
     مرئيه
    -0.41
    badges
    -0.39
    tská
    -0.39
    ModelBuilder
    -0.39
    POSITIVE LOGITS
     maksi
    0.94
     saar
    0.83
     duk
    0.78
     dises
    0.77
     naer
    0.75
     osal
    0.74
     alha
    0.73
     lü
    0.72
     lele
    0.70
     ilm
    0.69
    Activations Density 0.488%

    No Known Activations