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. 8218
    Prev
    Next
    INDEX
    Explanations

    references to the United States in political and security contexts

    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
    1145
    +0.13
    0.5%
    30
    +0.12
    0.4%
    1978
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.13
    0.04
    1527
    +0.12
    0.03
    1145
    +0.11
    0.04
    Negative Logits
     intptr
    -0.66
    DebuggerStep
    -0.62
    ScopeManager
    -0.61
     referenties
    -0.60
    Tē
    -0.60
    hyrchwyd
    -0.57
    HtmlAttribute
    -0.57
    <bos>
    -0.56
    Карьера
    -0.56
    पया
    -0.55
    POSITIVE LOGITS
     Juf
    1.44
     desir
    1.42
     fuf
    1.41
     inev
    1.40
     Mlle
    1.38
     guarante
    1.35
     unlaw
    1.35
     excru
    1.34
     perfet
    1.33
     increa
    1.33
    Activations Density 0.075%

    No Known Activations