© 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. 27857
    Prev
    Next
    INDEX
    Explanations

    expressions of confusion or misunderstanding

    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
    466
    +0.15
    0.9%
    40
    +0.12
    0.7%
    22
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.15
    0.02
    22
    +0.12
    0.02
    268
    +0.12
    0.02
    Negative Logits
    emen
    -1.84
    inai
    -1.65
    ynes
    -1.60
    folio
    -1.57
    nar
    -1.55
    bons
    -1.54
    illion
    -1.54
    eston
    -1.49
    ned
    -1.48
    aine
    -1.47
    POSITIVE LOGITS
    ±
    1.85
    ¥
    1.61
    Ń
    1.61
    ·
    1.58
    ŀ
    1.55
     warnings
    1.54
     lanes
    1.49
     diagnoses
    1.48
     diagnostic
    1.47
     tau
    1.47
    Activations Density 0.101%

    No Known Activations