© 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. 7622
    Prev
    Next
    INDEX
    Explanations

    phrases related to shelves or shelving

    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
    1974
    +0.20
    1.0%
    1678
    +0.14
    0.8%
    732
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1974
    +0.20
    0.03
    991
    +0.14
    0.03
    732
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.87
     acquaint
    -0.59
    Externí
    -0.57
     bring
    -0.57
     amass
    -0.55
    document
    -0.53
    Související
    -0.53
     empower
    -0.53
     perpetuate
    -0.52
     inaugurate
    -0.52
    POSITIVE LOGITS
     shelf
    1.53
     Shelf
    1.52
     shelves
    1.43
    shelf
    1.38
     Shelves
    1.37
    Shelf
    1.35
     shelving
    1.19
    Shel
    1.13
     habet
    1.09
     istan
    1.06
    Activations Density 0.320%

    No Known Activations