© 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. 10-RES-JB
    6. 1337
    Prev
    Next
    INDEX
    Explanations

    phrases related to delivery and appointment actions

    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
    +0.18
    0.7%
    1512
    +0.09
    0.4%
    667
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1512
    +0.18
    0.07
    1055
    +0.09
    0.06
    507
    +0.08
    0.06
    Negative Logits
    <bos>
    -3.21
    Autoritní
    -0.95
     للاسماء
    -0.82
    define
    -0.80
    RegressionTest
    -0.79
    IsContent
    -0.76
    setVerticalGroup
    -0.75
    HasIndex
    -0.75
    filepath
    -0.74
    MarshalTo
    -0.74
    POSITIVE LOGITS
     maneu
    2.73
     shenan
    2.62
     affor
    2.55
     lidl
    2.47
     reluct
    2.45
     stockholm
    2.44
     increa
    2.43
     milf
    2.43
     accla
    2.41
     unlaw
    2.41
    Activations Density 0.593%

    No Known Activations