© 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. 29549
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and public figures

    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
    410
    +0.17
    0.9%
    136
    +0.15
    0.8%
    101
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.17
    0.07
    40
    +0.15
    0.09
    352
    +0.12
    0.09
    Negative Logits
    <|outofrange|>
    -1.77
    -1.77
    -1.77
    -1.77
    -1.77
    <|outofrange|>
    -1.77
    ↵
    -1.77
    -1.77
    ↵↵
    -1.77
    ↵
    -1.77
    POSITIVE LOGITS
    lords
    1.61
    ided
    1.52
    stadt
    1.51
    ius
    1.47
    keit
    1.46
    iÄĩ
    1.42
    wic
    1.38
     whom
    1.38
     loose
    1.30
    aced
    1.29
    Activations Density 0.948%

    No Known Activations