© 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. 7278
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Steve."

    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
    +0.14
    1.0%
    1581
    +0.10
    0.7%
    1482
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.14
    0.03
    1581
    +0.10
    0.03
    1335
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.78
    ⓧ
    -1.05
    
    -0.89
    <?
    -0.89
     intersper
    -0.85
     amass
    -0.79
    /**
    -0.76
     endow
    -0.76
    <?
    -0.75
     disbur
    -0.68
    POSITIVE LOGITS
     Steve
    1.25
    Steve
    1.22
    STEVE
    1.05
     seksi
    1.01
     Minang
    0.99
     steve
    0.99
     Muhamma
    0.87
     kafe
    0.86
     Meksi
    0.86
     saar
    0.84
    Activations Density 0.042%

    No Known Activations