© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5057
    Prev
    Next
    INDEX
    Explanations

    words related to international relations or political situations

    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
    +0.11
    0.4%
    1616
    +0.10
    0.4%
    1602
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    666
    +0.11
    0.05
    1363
    +0.10
    0.05
    1490
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.56
    Prest
    -0.58
    Vegeu
    -0.58
    අ
    -0.57
     earn
    -0.57
     spread
    -0.56
     gain
    -0.56
     cur
    -0.56
    <?
    -0.55
    ආ
    -0.55
    POSITIVE LOGITS
     stockholm
    1.47
     toledo
    1.44
     peugeot
    1.39
     fta
    1.37
     chrysler
    1.37
     frankfurt
    1.35
     panama
    1.34
     liverpool
    1.34
     hilton
    1.32
     Juf
    1.32
    Activations Density 0.890%

    No Known Activations