© 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. 29461
    Prev
    Next
    INDEX
    Explanations

    the repetitive and structural elements in prose, particularly focusing on phrases denoting functions and relationships

    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
    93
    +0.11
    0.6%
    172
    +0.11
    0.6%
    476
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.11
    0.02
    172
    +0.11
    0.01
    157
    +0.11
    0.03
    Negative Logits
    athi
    -2.08
    water
    -1.60
    pur
    -1.58
    agraph
    -1.50
    enta
    -1.49
     cents
    -1.46
     miles
    -1.45
    bul
    -1.43
    LINE
    -1.43
    oles
    -1.41
    POSITIVE LOGITS
    ĥ½
    3.07
    ¥
    2.75
    §
    2.73
    Į
    2.60
    ļ
    2.57
    Ĩ
    2.57
    ĸ´
    2.53
    µ
    2.51
    ½
    2.45
    ¹
    2.43
    Activations Density 0.345%

    No Known Activations