© 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. 29256
    Prev
    Next
    INDEX
    Explanations

    code snippets related to file management and manipulation

    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%
    416
    +0.13
    0.7%
    53
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.16
    0.10
    438
    +0.13
    0.07
    416
    +0.13
    0.04
    Negative Logits
    agem
    -1.69
    sheet
    -1.61
    etter
    -1.59
    omics
    -1.50
    styles
    -1.50
     direction
    -1.48
    ){#
    -1.47
    ceedings
    -1.45
     perspectives
    -1.42
    ág
    -1.41
    POSITIVE LOGITS
     dams
    1.60
     lamb
    1.56
     LORD
    1.50
     peace
    1.39
     DU
    1.38
    der
    1.33
     fuckin
    1.33
     sheep
    1.33
    FFIR
    1.31
    king
    1.30
    Activations Density 0.816%

    No Known Activations