© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 257
    Prev
    Next
    INDEX
    Explanations

    terms related to usability and user experience

    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
    1870
    +0.12
    0.4%
    1218
    +0.06
    0.2%
    501
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.12
    0.03
    1137
    +0.06
    0.05
    1870
    +0.06
    0.02
    Negative Logits
    <bos>
    -1.33
    /**
    -0.81
    
    -0.74
    ⓧ
    -0.72
    //
    -0.71
    <?
    -0.70
     so
    -0.67
     put
    -0.66
     do
    -0.66
    #
    -0.66
    POSITIVE LOGITS
     jaya
    1.83
     bandung
    1.82
     chèvre
    1.72
     matel
    1.72
     lele
    1.68
     !...
    1.63
     provence
    1.62
     wien
    1.62
     bordeaux
    1.61
     jawa
    1.60
    Activations Density 0.225%

    No Known Activations