© 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. 10-RES-JB
    11. 4050
    Prev
    Next
    INDEX
    Explanations

    terms related to auctions and sales

    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
    783
    +0.18
    0.8%
    50
    +0.15
    0.7%
    1757
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.18
    0.02
    1971
    +0.15
    0.01
    406
    +0.13
    0.01
    Negative Logits
    <bos>
    -2.17
    /*++
    -0.64
     trí
    -0.63
    InputBorder
    -0.63
    <0xF0>
    -0.61
    avras
    -0.61
     sit
    -0.60
    ঔ
    -0.60
    הח
    -0.59
    reg
    -0.59
    POSITIVE LOGITS
     🤣🤣
    1.58
     maneu
    1.57
     milf
    1.38
     emphat
    1.35
     lmfao
    1.34
     disagre
    1.34
     depic
    1.34
     bandung
    1.34
     reluct
    1.32
     😭😭
    1.32
    Activations Density 0.058%

    No Known Activations