© 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. 28360
    Prev
    Next
    INDEX
    Explanations

    phrases related to development and progress

    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
    23
    +0.16
    0.9%
    59
    +0.13
    0.7%
    75
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.16
    -0.00
    69
    +0.13
    0.03
    330
    +0.11
    0.01
    Negative Logits
    INGS
    -1.89
    ERY
    -1.51
    minster
    -1.45
    bilt
    -1.42
     Ramos
    -1.41
    piece
    -1.39
     Trophy
    -1.38
     Triton
    -1.38
    anza
    -1.36
    headed
    -1.34
    POSITIVE LOGITS
    ĵ
    2.03
     transition
    1.61
    ils
    1.55
    ľĵ
    1.52
     adults
    1.50
     females
    1.44
     spin
    1.43
    Ĭ
    1.40
    atal
    1.39
    ł
    1.39
    Activations Density 0.257%

    No Known Activations