© 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. 28654
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to limits or boundaries of context or topics

    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
    156
    +0.12
    0.7%
    364
    +0.10
    0.6%
    376
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    301
    +0.12
    0.01
    364
    +0.10
    0.01
    194
    +0.10
    0.01
    Negative Logits
    ureus
    -1.62
    öm
    -1.53
    rokee
    -1.45
    sole
    -1.36
     mourn
    -1.35
    ennes
    -1.35
    cred
    -1.35
    spir
    -1.34
    enty
    -1.34
    ylan
    -1.33
    POSITIVE LOGITS
    lei
    1.69
    imetry
    1.66
    etable
    1.65
    ably
    1.64
    vier
    1.60
    ively
    1.54
    IRT
    1.52
    iella
    1.49
    bent
    1.47
     irradiated
    1.46
    Activations Density 0.079%

    No Known Activations