© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11410
    Prev
    Next
    INDEX
    Explanations

    references to characters, events, or elements related to narratives and storytelling

    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
    156
    +0.36
    2.2%
    240
    +0.16
    1.0%
    293
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.36
    0.10
    400
    +0.16
    0.04
    240
    +0.13
    -0.02
    Negative Logits
    ÑĢÑĥг
    -2.00
    ŀ
    -1.73
    ·
    -1.72
    teenth
    -1.70
    áĢº
    -1.63
     slightest
    -1.55
                                     
    -1.55
    ↵		   
    -1.55
    č↵                   
    -1.55
     ↵     
    -1.55
    POSITIVE LOGITS
     (>
    1.75
     ()
    1.57
     (<
    1.50
    ipro
    1.49
    izability
    1.48
    /
    1.45
    itively
    1.44
     aids
    1.42
     slots
    1.41
     (“
    1.39
    Activations Density 2.687%

    No Known Activations