© 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. 29388
    Prev
    Next
    INDEX
    Explanations

    references to minimum quantities or standards

    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
    376
    +0.15
    0.8%
    327
    +0.13
    0.8%
    214
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.15
    0.01
    86
    +0.13
    0.02
    327
    +0.13
    0.02
    Negative Logits
    ½
    -2.24
    ĵ
    -2.16
    ¦
    -2.02
    ¾
    -2.01
    ¸
    -1.98
    ķ
    -1.96
    ¢
    -1.92
    ±
    -1.86
    ¹
    -1.86
    ¡
    -1.82
    POSITIVE LOGITS
     requirements
    1.87
     governing
    1.67
     wage
    1.64
     requirement
    1.61
    ermost
    1.58
    oplastic
    1.53
     amount
    1.52
     conceivable
    1.50
     aperture
    1.47
    imal
    1.47
    Activations Density 0.082%

    No Known Activations