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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-SM
    11. 12803
    Prev
    Next
    INDEX
    Explanations

    references to URLs in varying contexts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    148
    +0.13
    0.8%
    329
    +0.13
    0.7%
    89
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.13
    -0.00
    89
    +0.13
    0.02
    36
    +0.12
    0.03
    Negative Logits
    imals
    -1.74
    hire
    -1.69
    eu
    -1.62
    cember
    -1.54
    ively
    -1.49
     financially
    -1.48
     quarterly
    -1.48
     clinically
    -1.46
    thood
    -1.44
     yet
    -1.43
    POSITIVE LOGITS
    encoded
    2.67
    encode
    2.50
    Encode
    2.10
    Rewrite
    2.04
    finder
    1.98
    ://
    1.96
    Resolver
    1.90
     localhost
    1.89
    parse
    1.87
    ("/
    1.86
    Activations Density 0.179%

    No Known Activations