© 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. 13668
    Prev
    Next
    INDEX
    Explanations

    references to storytelling or recounting events and experiences

    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
    43
    +0.13
    0.7%
    148
    +0.12
    0.7%
    431
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.13
    0.01
    253
    +0.12
    0.05
    221
    +0.12
    0.04
    Negative Logits
    allocate
    -1.61
    wards
    -1.51
     advantage
    -1.50
    Zone
    -1.49
    starter
    -1.47
     Framework
    -1.43
    Drive
    -1.43
    ropolis
    -1.42
    avis
    -1.42
    Comp
    -1.40
    POSITIVE LOGITS
    itely
    1.71
    eted
    1.69
    inian
    1.62
     depicting
    1.57
     haunted
    1.56
    ¿½
    1.55
     aloud
    1.53
     evid
    1.51
     recalled
    1.48
     hor
    1.47
    Activations Density 0.997%

    No Known Activations