© 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. 29415
    Prev
    Next
    INDEX
    Explanations

    multiple occurrences of the preposition "in."

    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
    338
    +0.13
    0.8%
    179
    +0.12
    0.7%
    478
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.09
    243
    +0.12
    0.08
    4
    +0.11
    0.05
    Negative Logits
     refer
    -1.64
     unless
    -1.60
     &
    -1.59
     while
    -1.44
    onies
    -1.43
     since
    -1.41
     whenever
    -1.39
     etc
    -1.38
    ING
    -1.38
    vier
    -1.37
    POSITIVE LOGITS
    HECK
    1.63
    bred
    1.52
    built
    1.50
    ologous
    1.44
    stud
    1.43
    pless
    1.42
    ť
    1.40
    experienced
    1.39
    comings
    1.39
    appropri
    1.38
    Activations Density 0.686%

    No Known Activations