© 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. 4115
    Prev
    Next
    INDEX
    Explanations

    information related to wedding announcements

    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
    •fun features

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.16
    0.6%
    1520
    +0.12
    0.4%
    1964
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.16
    0.03
    1244
    +0.12
    0.03
    179
    +0.10
    0.03
    Negative Logits
    <bos>
    -1.76
    ⓧ
    -0.99
    /**
    -0.62
    #
    -0.57
    MessageOf
    -0.57
    SequentialGroup
    -0.56
    ècie
    -0.56
     todėl
    -0.56
    HasAnnotation
    -0.55
    ("")]
    -0.55
    POSITIVE LOGITS
     brides
    1.07
     bride
    1.07
     Bride
    0.97
     sposa
    0.94
     groom
    0.93
     Fulda
    0.91
     Brides
    0.91
     maroc
    0.90
     indestru
    0.90
     Glou
    0.89
    Activations Density 0.189%

    No Known Activations