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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2518
    Prev
    Next
    INDEX
    Explanations

    phrases related to compromise or balance

    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
    25
    +0.10
    0.3%
    90
    +0.10
    0.3%
    58
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1896
    +0.10
    0.02
    800
    +0.10
    0.02
    184
    +0.09
    0.01
    Negative Logits
    <bos>
    -0.81
    <?
    -0.69
    
    -0.68
     annihilated
    -0.64
    /**
    -0.64
     incarcer
    -0.63
     disreg
    -0.62
     leaped
    -0.62
     disbur
    -0.59
     annihil
    -0.58
    POSITIVE LOGITS
     compromise
    1.18
     Compromise
    1.18
     compromis
    1.10
    comprom
    1.09
     comprom
    0.97
     compromises
    0.95
    Comprom
    0.89
     ufe
    0.83
    compromised
    0.76
     paff
    0.75
    Activations Density 0.257%

    No Known Activations