© 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. 27803
    Prev
    Next
    INDEX
    Explanations

    suffixes related to biological terms and morphologies

    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
    438
    +0.13
    0.7%
    247
    +0.12
    0.7%
    7
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.13
    0.02
    509
    +0.12
    0.02
    386
    +0.11
    0.01
    Negative Logits
     single
    -1.72
     continents
    -1.66
     previous
    -1.58
     ourselves
    -1.56
     separate
    -1.54
    pecially
    -1.51
     few
    -1.50
     both
    -1.49
     dont
    -1.47
     track
    -1.45
    POSITIVE LOGITS
    arie
    2.20
    opoulos
    2.12
    ics
    1.89
    ript
    1.86
    itis
    1.83
    akis
    1.81
    ário
    1.79
    hematic
    1.77
    oked
    1.76
    osti
    1.75
    Activations Density 0.101%

    No Known Activations