© 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. 12923
    Prev
    Next
    INDEX
    Explanations

    discussions about cost and cost-effectiveness in various 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
    500
    +0.13
    0.7%
    351
    +0.12
    0.7%
    221
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.13
    0.03
    221
    +0.12
    0.03
    125
    +0.12
    0.03
    Negative Logits
    ij
    -2.12
    ¾
    -2.07
    ĨĴ
    -1.96
    Į
    -1.91
    º
    -1.91
    £
    -1.88
    IJ
    -1.81
    à±ģ
    -1.81
    à±
    -1.76
    ·¸
    -1.70
    POSITIVE LOGITS
    umers
    2.87
     savings
    2.82
    umed
    2.59
     incurred
    2.58
    lier
    2.42
    liest
    2.24
    umer
    2.17
    uming
    2.14
    umes
    2.10
    ochond
    2.02
    Activations Density 0.156%

    No Known Activations