© 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. 27056
    Prev
    Next
    INDEX
    Explanations

    references to "stream" and its variations in the context of data handling or media consumption

    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
    156
    +0.20
    1.1%
    144
    +0.14
    0.8%
    391
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.20
    0.01
    17
    +0.14
    0.00
    173
    +0.11
    0.01
    Negative Logits
    ľĵ
    -2.28
    ĥ½
    -2.18
    yahoo
    -1.83
    ¥
    -1.83
     behalf
    -1.76
    Ĩ
    -1.73
    ypse
    -1.68
    §
    -1.67
    ISA
    -1.55
    ¸
    -1.54
    POSITIVE LOGITS
    lined
    2.33
    gun
    2.19
    chan
    1.93
     onto
    1.87
    bank
    1.86
    lining
    1.77
    liner
    1.68
    ings
    1.66
    chn
    1.61
    pipe
    1.60
    Activations Density 0.128%

    No Known Activations