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. 15024
    Prev
    Next
    INDEX
    Explanations

    references to hypothetical or post-apocalyptic scenarios involving the extinction of humanity and the potential discovery by aliens of past civilizations on Earth

    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
    +0.27
    1.0%
    856
    +0.08
    0.3%
    1385
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2015
    +0.27
    0.00
    1253
    +0.08
    0.03
    558
    +0.07
    0.04
    Negative Logits
    <bos>
    -1.83
     reappeared
    -0.74
    /***
    
    -0.71
     winked
    -0.71
     shuddered
    -0.70
     inaugurate
    -0.70
     localize
    -0.70
     rehabilitate
    -0.69
     reinstate
    -0.69
     reappear
    -0.67
    POSITIVE LOGITS
     véhic
    1.04
     soulign
    0.97
     préc
    0.91
     pylab
    0.91
     décid
    0.88
     commandés
    0.85
     réjou
    0.85
     heapq
    0.82
     bourg
    0.81
     ecru
    0.81
    Activations Density 1.606%

    No Known Activations