© 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 EvalsExportsAPI 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. 27511
    Prev
    Next
    INDEX
    Explanations

    references to various model types in programming or systems

    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
    156
    +0.18
    1.0%
    392
    +0.16
    0.9%
    140
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.18
    0.04
    140
    +0.16
    0.03
    95
    +0.12
    0.03
    Negative Logits
     latter
    -1.69
    rapy
    -1.67
    woke
    -1.66
    dding
    -1.55
    idel
    -1.51
    7554
    -1.47
    ceq
    -1.46
    reduc
    -1.41
    itely
    -1.41
    stitutes
    -1.39
    POSITIVE LOGITS
     herself
    2.35
     captures
    2.06
    ical
    1.78
    ERTY
    1.73
    eless
    1.65
     knows
    1.64
    port
    1.64
    erne
    1.62
    oft
    1.59
    endez
    1.51
    Activations Density 0.130%

    No Known Activations