© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 28699
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure

    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
    407
    +0.14
    0.8%
    466
    +0.14
    0.8%
    478
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.14
    0.15
    46
    +0.14
    0.05
    53
    +0.12
    0.13
    Negative Logits
    !).
    -1.74
    idenote
    -1.48
    !!!
    -1.45
     schools
    -1.34
     footing
    -1.32
     Starbucks
    -1.31
     [âĢ¦]
    -1.31
     stature
    -1.30
     ball
    -1.28
    school
    -1.28
    POSITIVE LOGITS
    ↵
    1.75
    omitempty
    1.61
     /*!<
    1.54
    imon
    1.52
    ↵
    1.48
     /**<
    1.47
    erred
    1.45
     meta
    1.44
     ///<
    1.42
    ↵
    1.42
    Activations Density 3.192%

    No Known Activations