© 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. 4198
    Prev
    Next
    INDEX
    Explanations

    mentions of lease-related terms and legal agreements

    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
    32
    +0.18
    0.9%
    341
    +0.16
    0.8%
    169
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.18
    0.03
    1870
    +0.16
    0.01
    1059
    +0.15
    0.03
    Negative Logits
    <bos>
    -0.96
     Salut
    -0.56
    polazione
    -0.55
     Pont
    -0.54
     Scor
    -0.54
    uxxxx
    -0.53
     spont
    -0.53
     rek
    -0.53
    McC
    -0.53
     jette
    -0.52
    POSITIVE LOGITS
     lease
    1.25
     leases
    1.11
    Lease
    1.11
     Lease
    1.10
    lease
    1.02
     leasing
    1.00
     leased
    0.97
    LEASE
    0.90
     Leasing
    0.86
     swarovski
    0.83
    Activations Density 0.476%

    No Known Activations