© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 28725
    Prev
    Next
    INDEX
    Explanations

    instances of the term "Sch" or its variations, indicating a focus on the significance or mention of someone or something related to that term

    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
    +0.28
    1.6%
    59
    +0.16
    0.9%
    111
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.28
    0.03
    369
    +0.16
    0.02
    424
    +0.13
    0.02
    Negative Logits
    printStackTrace
    -1.65
    acting
    -1.64
    TRODUCTION
    -1.60
    ocular
    -1.47
    estion
    -1.45
    rfloor
    -1.44
    rowser
    -1.43
    atorial
    -1.42
    ating
    -1.41
    ection
    -1.41
    POSITIVE LOGITS
    nee
    1.77
    wan
    1.64
    izophren
    1.59
    war
    1.48
    mong
    1.45
    rij
    1.41
    izo
    1.40
    ifer
    1.38
    (%
    1.35
    los
    1.34
    Activations Density 0.067%

    No Known Activations