© 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. 2-RES-SM
    11. 31044
    Prev
    Next
    INDEX
    Explanations

    elements related to technical specifications and configurations of ports and data streams

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    382
    +0.17
    1.0%
    98
    +0.16
    0.9%
    479
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.17
    0.11
    479
    +0.16
    0.06
    264
    +0.15
    0.17
    Negative Logits
     bedrooms
    -1.43
     Fashion
    -1.43
    coming
    -1.41
    esque
    -1.37
    acious
    -1.33
     editorial
    -1.33
     approval
    -1.32
     acceptance
    -1.32
     Freedom
    -1.32
     exceptional
    -1.31
    POSITIVE LOGITS
    ľĵ
    2.04
    anus
    1.85
    .+
    1.61
    malloc
    1.48
    lez
    1.46
    ethylene
    1.43
    blogspot
    1.41
    umably
    1.41
    unnable
    1.41
    pite
    1.39
    Activations Density 5.046%

    No Known Activations