© 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. 29095
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "google" and its associated services and libraries

    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
    369
    +0.14
    0.8%
    246
    +0.12
    0.7%
    372
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.14
    0.02
    252
    +0.12
    0.01
    246
    +0.12
    0.02
    Negative Logits
     ending
    -1.59
     outcome
    -1.52
    ges
    -1.49
    sen
    -1.44
    ften
    -1.43
     outcomes
    -1.43
    matically
    -1.42
     slightest
    -1.41
    issions
    -1.40
    GE
    -1.39
    POSITIVE LOGITS
    fonts
    1.88
    ument
    1.72
    joy
    1.62
    wald
    1.60
    adier
    1.60
    liche
    1.60
    ruptcy
    1.59
    wall
    1.58
    cdn
    1.53
     Records
    1.51
    Activations Density 0.061%

    No Known Activations