© 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. 1926
    Prev
    Next
    INDEX
    Explanations

    terms of endearment or direct addresses with emotions attached

    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
    1451
    +0.10
    0.3%
    2030
    +0.10
    0.3%
    680
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2030
    +0.10
    0.02
    1451
    +0.10
    0.02
    260
    +0.07
    0.02
    Negative Logits
    ⓧ
    -0.78
    
    -0.77
    /**
    -0.67
    <bos>
    -0.63
    ModelAttribute
    -0.54
    esti
    -0.53
    build
    -0.52
    <?
    -0.52
    hist
    -0.50
     onStart
    -0.49
    POSITIVE LOGITS
     dear
    2.56
     Dear
    2.44
    dear
    2.26
    Dear
    2.19
     DEAR
    2.10
     dearest
    1.88
    DEAR
    1.82
    Dearest
    1.71
     lidl
    1.16
     dearly
    1.13
    Activations Density 0.134%

    No Known Activations