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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 74
    Prev
    Next
    INDEX
    Explanations

    references to casinos and gambling

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1178
    +0.15
    0.5%
    421
    +0.09
    0.3%
    1909
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1178
    +0.15
    0.03
    421
    +0.09
    0.02
    1591
    +0.07
    0.02
    Negative Logits
    <bos>
    -0.80
     expel
    -0.65
     endow
    -0.64
    /**
    -0.60
    beforeAll
    -0.59
    <?
    -0.58
    /*++
    -0.57
    <!--
    -0.56
     neutralize
    -0.56
     reinstate
    -0.55
    POSITIVE LOGITS
     Casino
    2.12
     casino
    2.02
    Casino
    1.92
    casino
    1.77
     Casinos
    1.76
     casinos
    1.71
    Gambling
    1.45
     gambling
    1.42
     Gambling
    1.29
     gamblers
    1.28
    Activations Density 0.132%

    No Known Activations