© 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. 77
    Prev
    Next
    INDEX
    Explanations

    phrases related to entertainment and leisure activities

    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
    50
    +0.07
    0.2%
    492
    +0.06
    0.2%
    783
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.07
    0.03
    2030
    +0.06
    0.02
    1861
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.12
    /***
    -0.83
     tegens
    -0.58
    public
    -0.57
    void
    -0.55
    ⓧ
    -0.55
    //---
    -0.55
    qiang
    -0.53
    send
    -0.52
    runApp
    -0.52
    POSITIVE LOGITS
     entertaining
    1.58
     entertain
    1.29
     entertained
    1.23
     Juf
    1.12
     fei
    1.08
     catég
    1.06
     sii
    1.06
     maneu
    1.06
     idr
    1.06
     fup
    1.05
    Activations Density 0.259%

    No Known Activations