© 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. 28587
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "of" as a preposition or part of a phrase indicating relationships

    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
    +0.18
    1.0%
    478
    +0.17
    1.0%
    39
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.18
    0.14
    156
    +0.17
    0.09
    271
    +0.12
    0.03
    Negative Logits
    Org
    -1.47
    arias
    -1.40
    oque
    -1.38
    IMO
    -1.38
     flashes
    -1.38
    rus
    -1.37
    fonts
    -1.35
     notices
    -1.32
    ior
    -1.31
    Card
    -1.31
    POSITIVE LOGITS
    ĵ
    3.27
    ij
    3.25
    ¿½
    3.02
    Ħ
    3.00
    ĥ½
    2.92
    ¼
    2.91
    Ķ
    2.87
    ķ
    2.85
    µ
    2.72
    ĥ
    2.71
    Activations Density 0.754%

    No Known Activations