© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6-RES-JB
    11. 6004
    Prev
    Next
    INDEX
    Explanations

    mentions of characters' names in a dialogue or interview setup

    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
    +0.19
    0.7%
    1842
    +0.15
    0.6%
    2015
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    836
    +0.19
    0.05
    823
    +0.15
    0.06
    510
    +0.10
    0.07
    Negative Logits
    <bos>
    -2.59
    
    -0.70
     uzyskać
    -0.68
    /***
    -0.68
    ⓧ
    -0.67
    <?
    -0.66
    <!--
    -0.62
    /*
    -0.61
    <?
    -0.59
     springfox
    -0.59
    POSITIVE LOGITS
     eiffel
    1.10
     cartier
    1.03
     stockholm
    0.99
     indestru
    0.99
     umbre
    0.95
     madonna
    0.95
     affor
    0.93
     effe
    0.92
     ecru
    0.91
     imposs
    0.91
    Activations Density 0.736%

    No Known Activations