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. 6802
    Prev
    Next
    INDEX
    Explanations

    information related to technology companies and their products, services, operations, and locations

    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
    +0.26
    1.0%
    198
    +0.10
    0.4%
    856
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.26
    0.10
    1252
    +0.10
    0.10
    856
    +0.08
    0.07
    Negative Logits
    <bos>
    -3.17
     Walkover
    -0.73
    addComponent
    -0.72
     initComponents
    -0.71
     put
    -0.70
     try
    -0.69
     serve
    -0.68
    public
    -0.68
     assume
    -0.68
     protect
    -0.68
    POSITIVE LOGITS
     affor
    2.51
     accla
    2.33
     increa
    2.32
     reluct
    2.25
     disagre
    2.22
     inev
    2.21
     maneu
    2.20
     unwarran
    2.20
     impra
    2.19
     Juf
    2.17
    Activations Density 1.614%

    No Known Activations