© 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. 7781
    Prev
    Next
    INDEX
    Explanations

    phrases related to acceleration or speed

    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
    889
    +0.16
    0.8%
    421
    +0.14
    0.7%
    1124
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    889
    +0.16
    0.04
    478
    +0.14
    0.02
    1896
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.65
     розта
    -0.66
    SuppressLint
    -0.62
     try
    -0.58
     жов
    -0.57
    var
    -0.57
     Paul
    -0.57
     близь
    -0.56
    Hoy
    -0.56
    Entidad
    -0.56
    POSITIVE LOGITS
     fte
    1.48
     acce
    1.44
     tew
    1.44
     stockholm
    1.43
     increa
    1.41
     dises
    1.40
     guarante
    1.40
     jaya
    1.38
     unden
    1.38
     ankara
    1.38
    Activations Density 0.466%

    No Known Activations