© 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. 6-RES-JB
    11. 2153
    Prev
    Next
    INDEX
    Explanations

    responses in a conversation that indicate agreement or understanding

    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
    +0.17
    0.6%
    1065
    +0.10
    0.4%
    1758
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1079
    +0.17
    0.03
    1363
    +0.10
    0.03
    1490
    +0.09
    0.03
    Negative Logits
    <bos>
    -1.80
    
    -0.91
    ⓧ
    -0.91
    /***
    -0.83
    /**
    -0.82
    <?
    -0.79
    <?
    -0.73
    /*
    -0.67
     ajudá
    -0.66
    SourceChecksum
    -0.65
    POSITIVE LOGITS
     despotism
    0.87
     signora
    0.81
    idance
    0.79
     pymysql
    0.77
     marié
    0.74
     skimage
    0.73
     nod
    0.72
     nods
    0.71
     blessé
    0.70
    haviour
    0.70
    Activations Density 0.191%

    No Known Activations