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. 2858
    Prev
    Next
    INDEX
    Explanations

    segments related to legislative discussions

    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
    +0.11
    0.3%
    946
    +0.09
    0.2%
    344
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.11
    0.05
    1428
    +0.09
    0.03
    1748
    +0.08
    0.02
    Negative Logits
     ecru
    -0.68
    pushd
    -0.67
     tricot
    -0.61
     strto
    -0.56
     conftest
    -0.54
    marginHorizontal
    -0.54
     considér
    -0.53
     strdup
    -0.52
     blockSize
    -0.52
    úsqueda
    -0.51
    POSITIVE LOGITS
     protokol
    0.88
     Bibl
    0.83
     kriminal
    0.82
     alkoh
    0.79
     keramik
    0.77
     presenters
    0.75
     kritis
    0.74
     Öster
    0.73
     akade
    0.73
     solidar
    0.73
    Activations Density 0.659%

    No Known Activations