© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 24717
    Prev
    Next
    INDEX
    Explanations

    references to the contents of files or packages

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    365
    +0.17
    0.9%
    490
    +0.14
    0.8%
    163
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.17
    0.02
    54
    +0.14
    0.02
    490
    +0.13
    0.01
    Negative Logits
    ¯
    -3.96
    §
    -3.71
    ↵
    -3.60
    ↵
    -3.60
    ↵
    -3.60
    ↵
    -3.60
    ↵
    -3.60
    ↵
    -3.60
    ↵    ↵
    -3.60
     ↵
    -3.60
    POSITIVE LOGITS
    ious
    1.91
    pective
    1.87
    Of
    1.72
     Of
    1.66
    ensory
    1.66
    ervation
    1.64
    icles
    1.63
    cribed
    1.62
    idium
    1.62
     minister
    1.61
    Activations Density 0.111%

    No Known Activations