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. 794
    Prev
    Next
    INDEX
    Explanations

    mention of different programs, agreements, community benefits, neighborhood initiatives, and infrastructure projects

    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
    161
    +0.19
    1.0%
    889
    +0.17
    0.9%
    812
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    889
    +0.19
    0.05
    783
    +0.17
    0.04
    161
    +0.16
    0.04
    Negative Logits
     shenan
    -1.10
     hairc
    -1.01
     hoody
    -0.97
     milf
    -0.96
     wikihow
    -0.93
     hentai
    -0.91
     lmfao
    -0.91
     Lmao
    -0.90
     increa
    -0.88
     disreg
    -0.88
    POSITIVE LOGITS
     designer
    0.92
     Mos
    0.89
    designer
    0.88
     Designer
    0.86
    Mos
    0.82
    Designer
    0.81
     warehouse
    0.70
     designers
    0.70
     canvas
    0.69
     kos
    0.67
    Activations Density 0.746%

    No Known Activations