© 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. 1-RES-SM
    11. 25891
    Prev
    Next
    INDEX
    Explanations

    the possessive pronoun "my."

    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
    478
    +0.18
    1.0%
    410
    +0.13
    0.8%
    176
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.18
    0.04
    96
    +0.13
    0.03
    176
    +0.13
    0.03
    Negative Logits
    imetric
    -1.59
    Material
    -1.56
    imit
    -1.55
    imet
    -1.52
     surface
    -1.48
    xiv
    -1.45
    stood
    -1.44
    ines
    -1.42
     ![](
    -1.42
    ifi
    -1.40
    POSITIVE LOGITS
    xico
    2.35
    riad
    2.19
     favorite
    2.05
     own
    2.03
    ª
    2.01
    ¹
    1.92
    croft
    1.88
     favourite
    1.87
    anmar
    1.85
    ocardial
    1.78
    Activations Density 0.184%

    No Known Activations