© 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. 25282
    Prev
    Next
    INDEX
    Explanations

    key performance indicators or notable statistics

    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
    115
    +0.15
    0.8%
    70
    +0.12
    0.7%
    498
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.15
    0.03
    80
    +0.12
    0.03
    112
    +0.12
    0.03
    Negative Logits
    ames
    -1.66
    asti
    -1.60
    uler
    -1.57
    ats
    -1.50
    acker
    -1.49
    geb
    -1.45
    umb
    -1.45
    ammers
    -1.45
    ame
    -1.45
     dock
    -1.45
    POSITIVE LOGITS
    sufficient
    1.44
     instructive
    1.44
    eLife
    1.43
    ificantly
    1.37
     enlight
    1.37
    İ
    1.34
    \**
    1.34
     ~*
    1.32
     interesting
    1.31
    ĥ½
    1.30
    Activations Density 0.068%

    No Known Activations