© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 30153
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and software development

    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
    313
    +0.13
    0.7%
    198
    +0.12
    0.7%
    108
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.13
    0.15
    238
    +0.12
    0.11
    75
    +0.12
    0.12
    Negative Logits
    oelectric
    -1.53
    gni
    -1.45
     residue
    -1.43
    orov
    -1.41
    ostream
    -1.40
     curvature
    -1.40
    eria
    -1.39
    ruct
    -1.37
     number
    -1.37
    arest
    -1.37
    POSITIVE LOGITS
              ↵
    2.57
    ↵
    2.57
    <|outofrange|>
    2.57
     ↵
    2.57
    ↵
    2.57
    č↵
    2.57
    ↵            ↵
    2.57
    2.57
    č↵č↵
    2.57
    <|outofrange|>
    2.57
    Activations Density 3.347%

    No Known Activations