© 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. 25267
    Prev
    Next
    INDEX
    Explanations

    numerical sequences or data points, particularly in a structured format

    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
    258
    +0.14
    0.8%
    21
    +0.12
    0.7%
    336
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.14
    0.09
    203
    +0.12
    0.09
    136
    +0.12
    -0.00
    Negative Logits
    &
    -1.49
    áĢ¬
    -1.39
     !!
    -1.31
    boarding
    -1.28
    iversity
    -1.26
    nement
    -1.26
     coding
    -1.24
     tester
    -1.24
     typical
    -1.20
     systems
    -1.20
    POSITIVE LOGITS
    ĥ½
    1.71
    ī
    1.60
    ģ
    1.60
    elian
    1.60
    ĨĴ
    1.48
    ĩ
    1.44
    Ī
    1.41
    than
    1.39
    ľĵ
    1.39
    ®
    1.38
    Activations Density 0.607%

    No Known Activations