© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4836
    Prev
    Next
    INDEX
    Explanations

    the word "to" and related phrases indicating purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.38
    1.9%
    1328
    +0.13
    0.7%
    889
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.38
    0.04
    752
    +0.13
    0.04
    889
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.84
    /**
    -0.81
    ⓧ
    -0.81
    invokeLater
    -0.70
    SequentialGroup
    -0.70
     got
    -0.70
    <?
    -0.69
    int
    -0.69
    </thead>
    -0.68
     don
    -0.68
    POSITIVE LOGITS
     affor
    1.89
     squa
    1.86
     maneu
    1.85
     increa
    1.80
     fta
    1.80
     impra
    1.79
     stockholm
    1.77
     accla
    1.76
     frankfurt
    1.75
     wien
    1.75
    Activations Density 0.252%

    No Known Activations