© 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. 2-RES-SM
    11. 26626
    Prev
    Next
    INDEX
    Explanations

    specific ecological or botanical terminology

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    72
    +0.21
    1.2%
    47
    +0.12
    0.7%
    98
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    72
    +0.21
    0.14
    228
    +0.12
    0.08
    271
    +0.12
    -0.03
    Negative Logits
    awa
    -1.49
     tongues
    -1.40
     possibility
    -1.40
    fried
    -1.37
    comed
    -1.37
    erad
    -1.36
     mer
    -1.36
     tongue
    -1.35
     surprises
    -1.35
    acious
    -1.35
    POSITIVE LOGITS
     (@
    1.78
    vez
    1.48
    jel
    1.40
    ietal
    1.39
     Judges
    1.38
    ↵	↵
    1.37
    oles
    1.35
    Fig
    1.33
    iba
    1.32
     elsewhere
    1.31
    Activations Density 4.693%

    No Known Activations