© 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 EvalsExportsAPI 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. 25973
    Prev
    Next
    INDEX
    Explanations

    expressions related to visual perception and observation

    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
    331
    +0.12
    0.6%
    466
    +0.11
    0.6%
    268
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.12
    0.00
    505
    +0.11
    0.03
    330
    +0.10
    0.02
    Negative Logits
    ¿
    -2.17
    §
    -2.08
    Ķ
    -2.08
    ŀ
    -2.08
    Ľ
    -2.06
    ij
    -2.03
    Į
    -2.02
    ¿½
    -2.00
    ·¸
    -1.99
    ¥
    -1.96
    POSITIVE LOGITS
     mirrors
    1.52
    ké
    1.52
    ”)
    1.49
     awe
    1.48
    seeing
    1.47
     Telescope
    1.46
     Watch
    1.46
     radar
    1.42
     face
    1.38
     Galile
    1.34
    Activations Density 2.065%

    No Known Activations