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. 15498
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters or criminal activities

    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
    1842
    +0.27
    1.0%
    184
    +0.18
    0.7%
    1343
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.27
    0.03
    1842
    +0.18
    0.05
    1261
    +0.17
    0.01
    Negative Logits
    Rozmiar
    -0.66
     împre
    -0.66
    Wymiary
    -0.66
    Skład
    -0.65
    lxt
    -0.65
    Literat
    -0.64
    Cechy
    -0.63
    Materiał
    -0.63
    Wszyst
    -0.62
     véhic
    -0.61
    POSITIVE LOGITS
     revisor
    0.77
     polig
    0.73
    ...»
    0.72
     balon
    0.72
     moza
    0.71
     bronz
    0.71
     koc
    0.71
     biel
    0.69
     makro
    0.69
     kask
    0.69
    Activations Density 0.410%

    No Known Activations