© 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. 9668
    Prev
    Next
    INDEX
    Explanations

    proper nouns and terms associated with places or named entities

    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
    271
    +0.11
    0.7%
    81
    +0.11
    0.6%
    262
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.11
    0.10
    73
    +0.11
    0.06
    271
    +0.11
    -0.00
    Negative Logits
    ı
    -1.63
    »
    -1.56
    ©
    -1.55
     unintended
    -1.55
    fections
    -1.55
     burdens
    -1.54
    §
    -1.54
    ¦
    -1.53
     loads
    -1.53
    ľĵ
    -1.52
    POSITIVE LOGITS
    mith
    3.06
    pace
    2.86
    urface
    2.66
    creen
    2.63
    ystem
    2.62
    heet
    2.60
    chool
    2.50
    chaft
    2.41
    ource
    2.38
    helf
    2.35
    Activations Density 0.981%

    No Known Activations