© 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. 0-RES-JB
    11. 2167
    Prev
    Next
    INDEX
    Explanations

    words related to the fashion brand "Proenza Schouler"

    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
    1676
    +0.07
    0.2%
    819
    +0.07
    0.2%
    1333
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.07
    0.03
    1455
    +0.07
    0.03
    1333
    +0.07
    0.03
    Negative Logits
    sheng
    -0.69
    setDefault
    -0.69
    zhong
    -0.67
    qiang
    -0.66
    qiao
    -0.65
    xiang
    -0.63
     continue
    -0.63
    zheng
    -0.61
     but
    -0.61
    WriteLiteral
    -0.61
    POSITIVE LOGITS
    ou
    2.39
     affor
    2.12
     excru
    2.03
     increa
    1.98
     maneu
    1.94
     inev
    1.88
     accla
    1.83
     squa
    1.83
     emphat
    1.82
    OU
    1.81
    Activations Density 0.119%

    No Known Activations