© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3543
    Prev
    Next
    INDEX
    Explanations

    phrases related to business, entrepreneurship, and decision-making

    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
    1535
    +0.23
    0.8%
    382
    +0.20
    0.7%
    2034
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.23
    0.12
    1535
    +0.20
    0.09
    752
    +0.17
    0.06
    Negative Logits
     disagre
    -1.91
     impra
    -1.88
     increa
    -1.87
     reluct
    -1.85
     affor
    -1.84
     unwarran
    -1.79
     shenan
    -1.78
     maneu
    -1.78
     viciss
    -1.77
     embodi
    -1.77
    POSITIVE LOGITS
     But
    1.00
     And
    0.96
    <bos>
    0.95
     Италијани
    0.93
     Even
    0.91
     Then
    0.87
     They
    0.82
     It
    0.82
    ↵↵
    0.82
     In
    0.81
    Activations Density 0.508%

    No Known Activations