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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 29607
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    419
    +0.21
    1.3%
    198
    +0.19
    1.1%
    436
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.21
    0.10
    427
    +0.19
    0.07
    419
    +0.15
    0.07
    Negative Logits
    ¿½
    -3.66
    ¯
    -3.65
    ĥ½
    -3.64
    ¥
    -3.60
     ↵      
    -3.53
                       
    -3.53
         ↵ 
    -3.53
    <|outofrange|>
    -3.53
                           
    -3.53
           ↵ 
    -3.53
    POSITIVE LOGITS
     anymore
    1.44
    oubt
    1.34
    ondo
    1.34
     cups
    1.29
    gio
    1.29
     EDTA
    1.29
     whom
    1.28
    osity
    1.27
     CU
    1.26
     nor
    1.26
    Activations Density 2.348%

    No Known Activations