© 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. 31164
    Prev
    Next
    INDEX
    Explanations

    occurrences of URLs and related path components

    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
    156
    +0.19
    1.1%
    17
    +0.15
    0.9%
    397
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.19
    0.01
    329
    +0.15
    0.02
    298
    +0.13
    0.02
    Negative Logits
     suicide
    -1.60
     happier
    -1.54
    urane
    -1.53
    phrine
    -1.53
     minds
    -1.50
    eu
    -1.50
    urers
    -1.49
    isure
    -1.47
    cha
    -1.47
    mber
    -1.46
    POSITIVE LOGITS
    ://
    1.96
    encoded
    1.93
    ichlet
    1.68
     uri
    1.56
    encode
    1.56
    Encode
    1.51
    ARGS
    1.51
    aho
    1.50
    BG
    1.50
    adoc
    1.45
    Activations Density 0.118%

    No Known Activations