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. 2817
    Prev
    Next
    INDEX
    Explanations

    motivation or hesitation in sharing personal stories online

    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
    305
    +0.09
    0.2%
    198
    +0.07
    0.2%
    1510
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1166
    +0.09
    0.05
    1723
    +0.07
    0.04
    305
    +0.07
    0.04
    Negative Logits
     aussitôt
    -0.64
     sûrement
    -0.63
     soudain
    -0.61
     précédemment
    -0.61
     malheureusement
    -0.60
     justement
    -0.59
     vanta
    -0.57
    inerja
    -0.55
     lentement
    -0.55
     constamment
    -0.54
    POSITIVE LOGITS
     bandai
    0.54
     openly
    0.53
     smtplib
    0.51
     pymysql
    0.51
     admitting
    0.51
    Personendaten
    0.49
     admit
    0.48
     overtly
    0.48
     anything
    0.48
    zoon
    0.47
    Activations Density 0.306%

    No Known Activations