© 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. 7527
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations and businesses

    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
    +0.26
    1.0%
    1652
    +0.07
    0.3%
    1935
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1652
    +0.26
    0.05
    861
    +0.07
    0.06
    972
    +0.06
    0.06
    Negative Logits
    <bos>
    -2.36
    ⓧ
    -0.78
    <?
    -0.73
    
    -0.73
    /**
    -0.72
    protected
    -0.71
    SequentialGroup
    -0.71
    DeleteMapping
    -0.71
    /*
    -0.70
    //});
    -0.69
    POSITIVE LOGITS
     maneu
    2.46
     impra
    2.32
     accla
    2.30
     increa
    2.28
     affor
    2.26
     reluct
    2.22
     depic
    2.12
     shenan
    2.07
     resear
    2.07
     indestru
    2.06
    Activations Density 1.164%

    No Known Activations