© 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. 28634
    Prev
    Next
    INDEX
    Explanations

    references to programming-related error handling and request processing

    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
    47
    +0.13
    0.8%
    263
    +0.13
    0.7%
    407
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.13
    0.10
    219
    +0.13
    0.10
    95
    +0.12
    0.10
    Negative Logits
    ħ
    -3.30
    ĵ
    -2.88
    ¹
    -2.85
    ģ
    -2.82
    ij
    -2.78
    ĥ
    -2.70
    ´
    -2.70
    «
    -2.69
    ŀ
    -2.68
    ĻĤ
    -2.62
    POSITIVE LOGITS
     sanity
    1.83
     %>
    1.77
     $.
    1.64
    InstanceState
    1.61
    ↵
    1.59
     localhost
    1.59
     $('#
    1.59
    syscall
    1.59
     mysql
    1.58
     args
    1.57
    Activations Density 1.440%

    No Known Activations