© 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. 1928
    Prev
    Next
    INDEX
    Explanations

    greetings or welcome messages on websites

    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
    +0.10
    0.4%
    1642
    +0.05
    0.2%
    690
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    179
    +0.10
    0.03
    1789
    +0.05
    0.03
    1471
    +0.05
    0.03
    Negative Logits
    ⓧ
    -1.23
    <?
    -1.09
    
    -0.98
    /**
    -0.97
    /*
    -0.91
    #
    -0.81
    <bos>
    -0.79
    <?
    -0.73
    }{||
    -0.73
    /*++
    -0.72
    POSITIVE LOGITS
     affor
    2.15
     increa
    2.07
     maneu
    2.04
     inev
    1.98
     accla
    1.98
     stockholm
    1.96
     fortn
    1.96
     effe
    1.96
     embodi
    1.95
     secon
    1.92
    Activations Density 0.050%

    No Known Activations