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. 6780
    Prev
    Next
    INDEX
    Explanations

    mentions of rap music

    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
    1296
    +0.15
    0.7%
    1961
    +0.14
    0.7%
    31
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.15
    0.04
    1331
    +0.14
    0.03
    732
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.26
    /*
    -0.81
    
    
    -0.76
    /**
    -0.72
    /*!
    
    -0.72
    AddWithValue
    -0.68
    /**
    
    
    -0.66
    ніципа
    -0.63
    RuleContext
    -0.61
    <?
    -0.60
    POSITIVE LOGITS
     Rap
    1.24
     pymysql
    1.23
     rap
    1.18
     increa
    1.14
    Rap
    1.13
     Momb
    1.09
     disagre
    1.09
     tolerably
    1.08
     impractica
    1.07
     indor
    1.07
    Activations Density 0.461%

    No Known Activations