© 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. 24520
    Prev
    Next
    INDEX
    Explanations

    phrases or statements related to official documentation or technical disclosures

    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
    98
    +0.21
    1.2%
    111
    +0.18
    1.1%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.21
    0.07
    98
    +0.18
    0.01
    164
    +0.14
    0.05
    Negative Logits
     batches
    -1.47
     intervals
    -1.46
     wait
    -1.44
     cycles
    -1.43
     timestamp
    -1.42
    ALLOC
    -1.41
     '[
    -1.37
     lump
    -1.37
    ferroni
    -1.35
     consistency
    -1.35
    POSITIVE LOGITS
    »¿
    2.21
    ahu
    1.85
    rapeutics
    1.78
    ĨĴ
    1.73
     herein
    1.66
    ses
    1.61
    aceae
    1.60
    inois
    1.57
    iquity
    1.54
    mology
    1.52
    Activations Density 0.250%

    No Known Activations