© 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. 2750
    Prev
    Next
    INDEX
    Explanations

    the word "fabricating" or related forms of the word "fabric"

    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
    +0.15
    0.9%
    1068
    +0.12
    0.7%
    1562
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.15
    0.03
    1331
    +0.12
    0.03
    1806
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.83
     intersper
    -1.13
    ⓧ
    -1.10
    
    -0.94
     endow
    -0.93
     inaugurate
    -0.91
    /***
    -0.87
     enshr
    -0.83
    /**
    -0.82
     gratify
    -0.78
    POSITIVE LOGITS
     fabric
    1.29
    fabric
    1.16
    Fabric
    1.16
     Fabric
    1.12
     saar
    1.07
     fabrics
    1.04
     FABRIC
    0.92
     ananas
    0.89
    FABRIC
    0.88
     babi
    0.88
    Activations Density 0.107%

    No Known Activations