© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7619
    Prev
    Next
    INDEX
    Explanations

    words related to taking risks and business decisions involving risks

    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
    1077
    +0.11
    0.3%
    630
    +0.10
    0.3%
    341
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1876
    +0.11
    0.03
    630
    +0.10
    0.03
    1077
    +0.08
    0.04
    Negative Logits
     Cik
    -0.62
     pama
    -0.56
     assiste
    -0.56
     roul
    -0.55
     endom
    -0.54
     Ust
    -0.53
     Kär
    -0.52
     kani
    -0.51
     Komple
    -0.51
     Lég
    -0.51
    POSITIVE LOGITS
     risky
    1.01
     risk
    0.92
     risks
    0.88
     risked
    0.84
     gamble
    0.83
     Risks
    0.83
     risking
    0.82
     RISK
    0.81
     Risk
    0.81
    Risk
    0.78
    Activations Density 0.341%

    No Known Activations