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. 643
    Prev
    Next
    INDEX
    Explanations

    references to specific periods of time or durations

    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
    1741
    +0.19
    0.6%
    50
    +0.13
    0.4%
    1535
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1507
    +0.19
    0.03
    1602
    +0.13
    0.03
    1379
    +0.13
    0.04
    Negative Logits
     kwiet
    -0.72
     Hinblick
    -0.68
     ziua
    -0.63
     Secrétaire
    -0.61
     tanong
    -0.60
    idać
    -0.59
     betreff
    -0.59
    zondere
    -0.57
     huwa
    -0.56
    ypeł
    -0.55
    POSITIVE LOGITS
     robus
    0.83
     abnorm
    0.82
     Eks
    0.77
     Amerik
    0.77
     unan
    0.74
     Rektor
    0.74
     Senat
    0.73
     Verk
    0.73
     Vorm
    0.73
     praktik
    0.73
    Activations Density 0.086%

    No Known Activations