© 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. 1704
    Prev
    Next
    INDEX
    Explanations

    expressions or phrases starting with "Well"

    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
    50
    +0.11
    0.4%
    1265
    +0.08
    0.3%
    1671
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1058
    +0.11
    0.05
    1606
    +0.08
    0.04
    385
    +0.05
    0.04
    Negative Logits
    <bos>
    -1.70
    
    -1.29
    /**
    -1.22
    <?
    -1.14
    ⓧ
    -1.14
    <?
    -1.07
    /*
    -0.98
    #
    -0.97
    <tfoot>
    -0.81
    abetes
    -0.80
    POSITIVE LOGITS
     maneu
    2.58
     increa
    2.43
     affor
    2.39
     impra
    2.37
     accla
    2.35
     shenan
    2.33
     reluct
    2.33
     disagre
    2.32
     scrat
    2.29
     Juf
    2.24
    Activations Density 0.076%

    No Known Activations