© 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. 25484
    Prev
    Next
    INDEX
    Explanations

    references to home or housing concepts

    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
    477
    +0.14
    0.7%
    106
    +0.13
    0.7%
    6
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.14
    0.00
    211
    +0.13
    0.00
    312
    +0.13
    0.00
    Negative Logits
     lapar
    -1.87
    OMA
    -1.63
    imab
    -1.55
     intersections
    -1.55
    INGTON
    -1.47
    ISPR
    -1.44
     weddings
    -1.44
     conjugation
    -1.43
     genera
    -1.43
     follicles
    -1.42
    POSITIVE LOGITS
    assertEqual
    1.65
    expect
    1.63
    omitempty
    1.62
     `
    1.58
    azer
    1.58
    ach
    1.55
    rangle
    1.55
    itled
    1.52
     "`
    1.50
    oks
    1.49
    Activations Density 0.000%

    No Known Activations