© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1095
    Prev
    Next
    INDEX
    Explanations

    references to a specific news organization (CNN)

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1573
    +0.08
    0.2%
    690
    +0.07
    0.2%
    1351
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1351
    +0.08
    0.03
    1577
    +0.07
    0.03
    1178
    +0.07
    0.03
    Negative Logits
    ⓧ
    -0.97
    <?
    -0.97
    
    -0.83
     und
    -0.83
     im
    -0.82
     under
    -0.81
    <eos>
    -0.80
     won
    -0.79
    طع
    -0.78
     build
    -0.78
    POSITIVE LOGITS
     aen
    2.62
     fta
    2.56
     maneu
    2.55
     wien
    2.53
     thut
    2.53
     desir
    2.52
     seiz
    2.51
     tew
    2.50
     ftu
    2.49
     mef
    2.49
    Activations Density 0.168%

    No Known Activations