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. 1546
    Prev
    Next
    INDEX
    Explanations

    instances of time-related phrases and mentions of specific names

    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
    1081
    +0.07
    0.2%
    856
    +0.07
    0.2%
    1226
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    693
    +0.07
    0.03
    1081
    +0.07
    0.04
    59
    +0.07
    0.03
    Negative Logits
     encomp
    -1.08
     impra
    -1.05
     shenan
    -1.04
     indescri
    -1.04
     increa
    -1.03
     unspeak
    -1.01
     disagre
    -0.99
     intersper
    -0.98
     affor
    -0.95
     reluct
    -0.94
    POSITIVE LOGITS
     Spisak
    0.59
    LOAT
    0.59
     AssemblyProduct
    0.57
     PARSER
    0.56
    RTSC
    0.55
    はじめに
    0.55
     विश्वसनीयता
    0.54
    ValueStyle
    0.54
     للاسماء
    0.53
    sphase
    0.53
    Activations Density 0.279%

    No Known Activations