© 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. 27614
    Prev
    Next
    INDEX
    Explanations

    XML declaration statements and various XML tags

    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
    +0.22
    1.2%
    478
    +0.18
    1.1%
    111
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.22
    0.02
    334
    +0.18
    0.01
    351
    +0.15
    0.01
    Negative Logits
    utes
    -1.75
    engers
    -1.72
     {@
    -1.67
    ittal
    -1.66
    Haw
    -1.65
    onds
    -1.56
    iture
    -1.52
     distance
    -1.45
    ttes
    -1.45
    urs
    -1.44
    POSITIVE LOGITS
     otro
    1.54
    nex
    1.53
     bast
    1.53
    pero
    1.50
    Ľ
    1.50
    TRODUCTION
    1.44
    ubotu
    1.43
     sab
    1.41
     spare
    1.38
     envy
    1.35
    Activations Density 0.026%

    No Known Activations