© 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. 2-RES-SM
    11. 32034
    Prev
    Next
    INDEX
    Explanations

    imports and references to logging and system modules in code

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    28
    +0.15
    0.9%
    83
    +0.14
    0.8%
    293
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    28
    +0.15
    0.03
    53
    +0.14
    0.04
    37
    +0.12
    0.02
    Negative Logits
     Europeans
    -1.46
    ise
    -1.45
    opter
    -1.44
     contradiction
    -1.41
     lost
    -1.40
    bearing
    -1.39
    edge
    -1.38
    inian
    -1.37
     campaigns
    -1.36
    aret
    -1.36
    POSITIVE LOGITS
    ĨĴ
    2.45
    ij
    2.02
    ŀ
    2.01
    ½
    1.97
    ¾
    1.95
    Ĥ¬
    1.91
    Ĵ
    1.86
    ¬
    1.84
    ĭ
    1.84
    Īĺ
    1.79
    Activations Density 0.140%

    No Known Activations