© 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. 25158
    Prev
    Next
    INDEX
    Explanations

    references to invitations and invitation-related terms

    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
    282
    +0.17
    0.9%
    376
    +0.15
    0.8%
    450
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.09
    156
    +0.15
    0.05
    271
    +0.12
    0.03
    Negative Logits
    rifug
    -1.79
    sis
    -1.64
    unnumbered
    -1.60
    chos
    -1.57
    rift
    -1.57
    worm
    -1.51
    poons
    -1.44
    ciparum
    -1.44
    lla
    -1.42
    vel
    -1.40
    POSITIVE LOGITS
    ariate
    2.04
    ariance
    1.97
    asion
    1.94
    Ĵ
    1.81
    itrogen
    1.79
    ierno
    1.67
    olved
    1.58
    ocations
    1.58
    olve
    1.49
    ¨
    1.49
    Activations Density 0.402%

    No Known Activations