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

    Neuronpedia

    APICircuit 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. 5439
    Prev
    Next
    INDEX
    Explanations

    information related to setting properties in a web programming context

    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
    876
    +0.24
    1.2%
    1699
    +0.18
    0.9%
    678
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.24
    0.12
    876
    +0.18
    -0.02
    304
    +0.15
    -0.02
    Negative Logits
    <bos>
    -2.81
    ⓧ
    -1.02
    /**
    -1.02
    
    
    -0.97
    /*
    -0.95
    Pró
    -0.95
    SequentialGroup
    -0.94
    #
    -0.89
    <?
    -0.88
    Rusia
    -0.88
    POSITIVE LOGITS
     wien
    3.14
     napoli
    3.04
     milano
    3.01
     ?...
    2.96
     effe
    2.94
     doman
    2.88
     stockholm
    2.86
     increa
    2.86
     squa
    2.86
     affor
    2.85
    Activations Density 1.034%

    No Known Activations