© 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. 29066
    Prev
    Next
    INDEX
    Explanations

    references to informational elements or data

    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
    365
    +0.15
    0.9%
    503
    +0.14
    0.8%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.05
    156
    +0.14
    0.04
    130
    +0.14
    0.04
    Negative Logits
     deaf
    -1.76
    tics
    -1.67
    ĨĴ
    -1.54
    tig
    -1.53
    Ļª
    -1.52
    ]{}\
    -1.51
     vain
    -1.51
    sis
    -1.46
    ©
    -1.45
    abouts
    -1.44
    POSITIVE LOGITS
    ister
    2.05
    plist
    1.78
    cam
    1.75
    reader
    1.48
    izon
    1.48
     About
    1.47
    hist
    1.47
    frame
    1.45
    {'
    1.40
    ppo
    1.39
    Activations Density 0.367%

    No Known Activations