© 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. 25320
    Prev
    Next
    INDEX
    Explanations

    identifiers related to programming projects and code configuration

    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
    169
    +0.18
    1.0%
    445
    +0.12
    0.7%
    144
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    169
    +0.18
    0.06
    27
    +0.12
    0.12
    436
    +0.12
    0.14
    Negative Logits
    edly
    -1.77
    IJ
    -1.62
    ./
    -1.58
    bags
    -1.53
    lights
    -1.50
    cases
    -1.50
    lam
    -1.48
    ĨĴ
    -1.46
    suits
    -1.44
    ings
    -1.44
    POSITIVE LOGITS
     Biosystems
    1.59
    gon
    1.50
     Planck
    1.49
     County
    1.34
    chet
    1.32
     fixed
    1.30
     Enterprises
    1.30
     Machine
    1.26
     inactivated
    1.25
    gue
    1.25
    Activations Density 4.039%

    No Known Activations