© 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. 4-RES-SM
    11. 10615
    Prev
    Next
    INDEX
    Explanations

    the letter 'p' or words containing it

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    148
    +0.13
    0.8%
    354
    +0.13
    0.7%
    189
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.13
    0.04
    148
    +0.13
    0.03
    41
    +0.11
    0.04
    Negative Logits
    s
    -2.92
    tro
    -2.43
    tics
    -1.93
     respect
    -1.93
    lace
    -1.86
    o
    -1.76
    t
    -1.70
    lé
    -1.68
    roads
    -1.67
    nals
    -1.66
    POSITIVE LOGITS
    ipeline
    2.27
    ractical
    2.27
    relim
    2.13
    ictures
    2.10
    ursuant
    2.08
    aused
    2.02
    ulmonary
    2.01
    edia
    2.00
    unct
    2.00
    reliminary
    1.99
    Activations Density 0.082%

    No Known Activations