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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5699
    Prev
    Next
    INDEX
    Explanations

    keywords related to establishing and setting up various entities or initiatives, particularly in the context of business or projects

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.19
    1.1%
    2011
    +0.10
    0.6%
    1256
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1256
    +0.19
    0.03
    58
    +0.10
    0.02
    2004
    +0.10
    0.02
    Negative Logits
    <bos>
    -3.30
    ⓧ
    -0.68
    /***
    
    -0.68
    setClass
    -0.66
    MockBean
    -0.65
    HasIndex
    -0.63
    /*++
    -0.62
    /**
    -0.62
    ɵɵ
    -0.61
    XmlAccessorType
    -0.60
    POSITIVE LOGITS
     stockholm
    1.56
     wien
    1.54
     lele
    1.52
     ?...
    1.50
     fta
    1.48
     milf
    1.47
     thut
    1.46
     napoli
    1.45
     „,
    1.43
     applau
    1.43
    Activations Density 0.098%

    No Known Activations