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. 14675
    Prev
    Next
    INDEX
    Explanations

    text related to sports news and updates

    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
    108
    +0.15
    0.7%
    50
    +0.14
    0.6%
    344
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.15
    0.05
    1905
    +0.14
    0.21
    906
    +0.14
    -0.01
    Negative Logits
    <bos>
    -2.52
    /**
    -0.95
    
    
    -0.95
    ⓧ
    -0.94
    <?
    -0.89
    /***
    
    -0.88
     gratify
    -0.88
     Ename
    -0.84
     disbur
    -0.83
     endow
    -0.82
    POSITIVE LOGITS
     kosme
    1.60
     minimalis
    1.47
     alkoh
    1.41
     silikon
    1.40
     praktik
    1.36
     kriminal
    1.33
     uhr
    1.32
     panik
    1.30
     protokol
    1.25
     akut
    1.25
    Activations Density 5.175%

    No Known Activations