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. 11948
    Prev
    Next
    INDEX
    Explanations

    questions and answers related to public communication and information dissemination

    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
    92
    +0.15
    0.8%
    501
    +0.13
    0.7%
    324
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.15
    0.04
    92
    +0.13
    0.07
    253
    +0.12
    0.05
    Negative Logits
    ī
    -3.15
    ļ
    -3.05
    į
    -3.03
    <|outofrange|>
    -2.97
    ↵                
    -2.97
                                                              
    -2.97
                             
    -2.97
                                                                                  
    -2.97
                  
    -2.97
    ↵             
    -2.97
    POSITIVE LOGITS
     satisf
    1.61
     resp
    1.57
     liber
    1.51
    ishly
    1.49
     defin
    1.47
     suggestive
    1.47
     perm
    1.45
     "{
    1.45
     pestic
    1.45
    rass
    1.44
    Activations Density 0.884%

    No Known Activations