Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 26
    Prev
    Next
    INDEX
    Explanations

    words related to encapsulation and technological processes

    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
    1883
    +0.06
    0.2%
    540
    +0.06
    0.2%
    772
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.06
    0.01
    283
    +0.06
    0.01
    1363
    +0.06
    0.02
    Negative Logits
    <bos>
    -0.88
    eniably
    -0.70
    /***
    
    -0.67
    efeated
    -0.67
    /*!
    
    -0.63
    Distrito
    -0.63
    Пол
    -0.53
     bring
    -0.52
     get
    -0.51
    amaged
    -0.51
    POSITIVE LOGITS
    ulation
    1.94
    ulate
    1.93
    ulating
    1.78
    ulations
    1.76
    ulated
    1.74
    ulates
    1.73
    ULATION
    1.45
     thut
    1.40
     meis
    1.39
    ulator
    1.31
    Activations Density 0.202%

    No Known Activations