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. 14956
    Prev
    Next
    INDEX
    Explanations

    information related to infrastructure projects such as subway lines, transportation funding, and legislative bills

    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
    1978
    +0.20
    0.6%
    776
    +0.15
    0.4%
    478
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.20
    0.06
    1978
    +0.15
    0.05
    321
    +0.10
    0.05
    Negative Logits
     Româ
    -0.90
    strona
    -0.89
     Ottobre
    -0.87
     Luglio
    -0.86
     Giugno
    -0.84
     appunt
    -0.79
    nasel
    -0.77
     ghz
    -0.77
     Settembre
    -0.74
    comuna
    -0.74
    POSITIVE LOGITS
     friable
    0.56
     syner
    0.52
     noct
    0.51
     contex
    0.50
     SANS
    0.49
     suscep
    0.49
     dichoto
    0.48
     purplish
    0.48
     ordinate
    0.48
     attemp
    0.47
    Activations Density 0.233%

    No Known Activations