© 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. 7906
    Prev
    Next
    INDEX
    Explanations

    mentions regarding customer interaction and feedback in a business context

    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
    0.9%
    394
    +0.18
    0.9%
    1177
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.18
    0.20
    1473
    +0.18
    0.09
    1224
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.69
    󠁿
    -0.87
    .
    -0.85
    PerformLayout
    -0.85
    מבר
    -0.83
    /**
    -0.83
    //
    -0.81
    /*
    -0.80
    -0.80
    RuleContext
    -0.79
    POSITIVE LOGITS
     maneu
    2.71
     affor
    2.63
     increa
    2.63
     reluct
    2.62
     impra
    2.58
     disagre
    2.51
     inev
    2.46
     accla
    2.45
     suscep
    2.43
     shenan
    2.38
    Activations Density 6.371%
    No Known Activations