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. 586
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal stories or narratives

    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
    1133
    +0.16
    0.8%
    1482
    +0.14
    0.7%
    1451
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.16
    0.07
    468
    +0.14
    0.05
    478
    +0.13
    0.03
    Negative Logits
    <bos>
    -2.02
     vainly
    -1.08
    ⓧ
    -0.96
     miscon
    -0.90
     merrily
    -0.89
    
    
    -0.87
     effectually
    -0.86
    /*!
    
    -0.85
     triumphantly
    -0.85
     nobly
    -0.84
    POSITIVE LOGITS
    ly
    1.14
     tramont
    1.00
     Luglio
    0.94
     kasa
    0.94
     dott
    0.93
     kac
    0.92
     pank
    0.90
     umo
    0.89
     ristor
    0.89
     saar
    0.88
    Activations Density 1.682%

    No Known Activations