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. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 12056
    Prev
    Next
    INDEX
    Explanations

    the word "as" in 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
    176
    +0.12
    0.7%
    88
    +0.12
    0.7%
    121
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.12
    0.04
    88
    +0.12
    0.03
    123
    +0.11
    0.03
    Negative Logits
    forms
    -1.62
    hook
    -1.58
    skin
    -1.48
    ICATION
    -1.44
    times
    -1.39
    backs
    -1.38
    ities
    -1.38
    rections
    -1.38
    sburg
    -1.36
     attack
    -1.35
    POSITIVE LOGITS
    ĥ½
    2.39
    »¿
    2.33
    ↵                                       
    2.32
    ↵↵       
    2.32
    ↵↵                           
    2.32
                          
    2.32
    ↵  ↵ 
    2.32
    č↵                       
    2.32
                  
    2.32
    ↵                                
    2.32
    Activations Density 0.179%

    No Known Activations