© 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. 28484
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental settings or variables

    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
    470
    +0.12
    0.7%
    450
    +0.12
    0.6%
    184
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.04
    17
    +0.12
    0.03
    156
    +0.11
    0.03
    Negative Logits
    ){#
    -1.61
    lla
    -1.54
    ctors
    -1.52
    ¿½
    -1.51
    oles
    -1.49
     agarose
    -1.48
    matically
    -1.47
    quin
    -1.46
    Ĭ
    -1.45
    cutaneous
    -1.44
    POSITIVE LOGITS
    rails
    1.87
     scrutiny
    1.58
    ariate
    1.54
     reserves
    1.43
    sci
    1.41
    state
    1.40
    ivable
    1.40
    isters
    1.40
    uable
    1.39
     conventions
    1.38
    Activations Density 0.255%

    No Known Activations