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. 715
    Prev
    Next
    INDEX
    Explanations

    medical conditions or medical procedures

    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
    1150
    +0.14
    0.4%
    2034
    +0.13
    0.4%
    1699
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1438
    +0.14
    0.03
    1720
    +0.13
    0.02
    1314
    +0.10
    0.04
    Negative Logits
     anzi
    -1.03
     specialmente
    -0.99
     purtroppo
    -0.97
     perciò
    -0.92
     poichè
    -0.85
     persino
    -0.83
    Autoritní
    -0.81
    tvguidetime
    -0.81
     sappi
    -0.81
    Переваги
    -0.81
    POSITIVE LOGITS
     alip
    0.63
    havior
    0.58
    bringer
    0.57
    haviour
    0.57
    .
    0.57
     göm
    0.54
    erequisites
    0.53
    mbda
    0.52
    erequisite
    0.52
    esterday
    0.51
    Activations Density 0.418%

    No Known Activations