Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5333
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical locations and development

    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
    +0.21
    1.2%
    645
    +0.12
    0.7%
    196
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    645
    +0.21
    0.05
    1052
    +0.12
    0.03
    196
    +0.10
    0.04
    Negative Logits
    <bos>
    -3.57
    <?
    -0.81
     put
    -0.76
    ⓧ
    -0.73
     create
    -0.72
    /***
    
    -0.72
    /**
    
    -0.69
     operate
    -0.68
     get
    -0.68
    public
    -0.67
    POSITIVE LOGITS
     wien
    1.81
     affor
    1.74
     stockholm
    1.73
     🤣🤣
    1.72
     desir
    1.71
     maneu
    1.71
     effe
    1.70
     fei
    1.69
     mef
    1.68
     ftu
    1.68
    Activations Density 0.112%

    No Known Activations