© 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. 26622
    Prev
    Next
    INDEX
    Explanations

    the phrase "In" used at the beginning of sentences or sections

    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
    +0.55
    4.2%
    111
    +0.52
    4.0%
    71
    +0.10
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    4
    +0.55
    0.02
    71
    +0.52
    0.02
    156
    +0.10
    0.02
    Negative Logits
    ij
    -1.93
    ľĵ
    -1.92
    ®
    -1.90
    Ľ
    -1.87
    ¥
    -1.84
    Īĺ
    -1.76
    ĺ
    -1.70
    ¢
    -1.68
    ·
    -1.66
    ©
    -1.63
    POSITIVE LOGITS
    fluence
    1.60
    frastructure
    1.56
     vitro
    1.51
     order
    1.46
    stances
    1.43
     spite
    1.41
     contrast
    1.38
    flu
    1.28
     recent
    1.25
     relation
    1.23
    Activations Density 0.014%

    No Known Activations