© 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. 29517
    Prev
    Next
    INDEX
    Explanations

    terms related to biological processes and mechanisms involving cellular functions and interactions

    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
    207
    +0.13
    0.8%
    452
    +0.13
    0.7%
    127
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.13
    0.05
    156
    +0.13
    0.07
    256
    +0.12
    0.05
    Negative Logits
     share
    -1.76
     named
    -1.75
     writ
    -1.64
     educated
    -1.57
     dotted
    -1.56
    owned
    -1.56
     Jewish
    -1.54
     refer
    -1.51
     interested
    -1.49
     concerned
    -1.48
    POSITIVE LOGITS
    Ĵ
    2.54
    Ļ
    2.36
    Ŀ
    2.28
    2.25
    ↵
    2.25
    ↵↵
    2.25
       ↵
    2.25
    ↵
    2.25
    2.25
    ↵
    2.25
    Activations Density 0.625%

    No Known Activations