© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 31777
    Prev
    Next
    INDEX
    Explanations

    references to tracking or saving data related to music and its metadata

    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
    17
    +0.20
    1.1%
    141
    +0.11
    0.6%
    74
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    141
    +0.20
    0.05
    154
    +0.11
    0.09
    102
    +0.10
    0.03
    Negative Logits
    Ĺ
    -2.27
    ŀ
    -2.25
    ¤
    -2.23
    ĻĤ
    -2.18
    Į
    -2.15
    ĸ
    -2.12
    ³
    -2.09
    ¿½
    -2.04
    Ŀ
    -2.03
    Ł
    -2.02
    POSITIVE LOGITS
    iff
    1.54
    ictionary
    1.50
     spreadsheet
    1.45
    osphere
    1.40
    ystems
    1.39
     quantities
    1.38
     públic
    1.37
    iffs
    1.35
     calculates
    1.33
     PDF
    1.33
    Activations Density 2.700%

    No Known Activations