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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12315
    Prev
    Next
    INDEX
    Explanations

    terms and structures related to programming and data handling in a coding context

    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
    72
    +0.12
    0.7%
    17
    +0.12
    0.7%
    231
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.12
    0.03
    252
    +0.12
    0.07
    271
    +0.11
    -0.00
    Negative Logits
     fertility
    -1.60
     clarity
    -1.59
    accur
    -1.42
     quality
    -1.39
     multivariate
    -1.38
     simplicity
    -1.37
    appropriate
    -1.37
    afa
    -1.36
    cancers
    -1.33
    ubunt
    -1.33
    POSITIVE LOGITS
    (@"
    1.84
    Formatter
    1.82
    FromString
    1.78
    Ptr
    1.58
    Runner
    1.57
     Pradesh
    1.52
    Builder
    1.52
    UMENT
    1.48
    Extensions
    1.46
    Parser
    1.45
    Activations Density 0.826%

    No Known Activations