© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1315
    Prev
    Next
    INDEX
    Explanations

    references to violent activities and discussions around violence

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.18
    1.1%
    1870
    +0.11
    0.6%
    1053
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.18
    0.03
    699
    +0.11
    0.03
    144
    +0.10
    0.02
    Negative Logits
    <bos>
    -3.60
    <?
    -0.76
    ⓧ
    -0.70
    /**
    -0.70
    
    -0.69
    find
    -0.67
     find
    -0.66
    register
    -0.66
    public
    -0.65
    Показать
    -0.65
    POSITIVE LOGITS
     affor
    1.81
     stockholm
    1.77
     Juf
    1.73
     wien
    1.70
     lidl
    1.69
     casio
    1.68
     desir
    1.67
     emphat
    1.67
     squa
    1.67
     guarante
    1.66
    Activations Density 0.087%

    No Known Activations