© 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. 29496
    Prev
    Next
    INDEX
    Explanations

    references to AJAX technology and alert functions

    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
    156
    +0.25
    1.5%
    37
    +0.12
    0.7%
    421
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.25
    0.06
    156
    +0.12
    0.04
    17
    +0.12
    0.03
    Negative Logits
     smallest
    -1.63
     apart
    -1.49
     largest
    -1.47
    ermost
    -1.44
     latter
    -1.43
     entire
    -1.39
     Lesser
    -1.37
     circum
    -1.37
    shaped
    -1.36
     examined
    -1.36
    POSITIVE LOGITS
    ¥
    1.84
    irez
    1.77
    ://
    1.73
     yourself
    1.58
    press
    1.54
    WARD
    1.54
    £
    1.50
    rpc
    1.49
    onaut
    1.45
    aho
    1.44
    Activations Density 0.216%

    No Known Activations