© 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. 29198
    Prev
    Next
    INDEX
    Explanations

    references to metrics or measurements, particularly in a technical or data-driven context

    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
    +0.15
    0.9%
    457
    +0.14
    0.8%
    203
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    457
    +0.15
    0.02
    348
    +0.14
    0.02
    9
    +0.12
    0.01
    Negative Logits
     throat
    -1.75
    ided
    -1.56
    TRODUCTION
    -1.53
     stomach
    -1.51
    hift
    -1.51
    aying
    -1.51
    idious
    -1.50
    otted
    -1.44
    pecially
    -1.43
    ffected
    -1.41
    POSITIVE LOGITS
    ropolis
    2.92
    ropol
    2.42
    eor
    2.18
    formin
    1.98
    aphys
    1.94
    ropolitan
    1.82
    rex
    1.67
    rol
    1.62
    ved
    1.59
    tech
    1.58
    Activations Density 0.062%

    No Known Activations