© 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. 2183
    Prev
    Next
    INDEX
    Explanations

    names of a specific person "Jon."

    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
    1178
    +0.10
    0.4%
    971
    +0.09
    0.3%
    204
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.10
    0.03
    78
    +0.09
    0.02
    1053
    +0.08
    0.02
    Negative Logits
    /**
    -0.90
    <?
    -0.81
    
    -0.78
    ⓧ
    -0.73
    /*
    -0.66
     shuddered
    -0.63
     clutched
    -0.57
     serce
    -0.57
     stabilize
    -0.55
     resorted
    -0.55
    POSITIVE LOGITS
     Jon
    2.22
    Jon
    2.11
     JON
    1.68
     jon
    1.65
    JON
    1.27
     applau
    1.11
     quoique
    1.10
     volon
    1.09
     tantôt
    1.04
     habile
    1.03
    Activations Density 0.177%

    No Known Activations