© 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. 1-RES-SM
    11. 26329
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations related to various organizations or terms

    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
    369
    +0.28
    1.6%
    156
    +0.19
    1.1%
    410
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.28
    0.19
    423
    +0.19
    0.12
    410
    +0.13
    0.13
    Negative Logits
    lasses
    -1.82
    ations
    -1.63
    rapeutics
    -1.61
    ção
    -1.58
    ties
    -1.58
    denly
    -1.57
    ging
    -1.56
    sible
    -1.56
    orph
    -1.51
    ÏĦαι
    -1.50
    POSITIVE LOGITS
    ®
    2.47
    ¬
    2.42
    ĸ
    2.27
    Ĵ
    2.21
    ī
    2.20
    ·
    2.16
    º
    2.15
    Ľ
    2.11
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    2.08
    «
    2.07
    Activations Density 0.937%

    No Known Activations