© 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. 4-RES-SM
    11. 9185
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to mechanical components and their configurations

    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
    466
    +0.24
    1.4%
    307
    +0.17
    1.0%
    309
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.24
    0.11
    309
    +0.17
    0.07
    47
    +0.12
    0.06
    Negative Logits
    imester
    -1.62
     philosophy
    -1.61
    rbrack
    -1.61
    ción
    -1.60
    pancy
    -1.60
    ingale
    -1.60
    reason
    -1.59
    ertation
    -1.59
    theorem
    -1.58
    endment
    -1.54
    POSITIVE LOGITS
     themselves
    2.71
     assemblies
    2.44
     poles
    2.43
     belts
    2.38
     cables
    2.37
     plates
    2.36
     openings
    2.33
     cylinders
    2.33
     widths
    2.32
     rods
    2.31
    Activations Density 1.367%

    No Known Activations