© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-SM
    11. 11010
    Prev
    Next
    INDEX
    Explanations

    terms related to military or governmental oversight and scrutiny

    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
    302
    +0.17
    1.0%
    240
    +0.17
    0.9%
    293
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.17
    0.07
    293
    +0.17
    0.11
    321
    +0.14
    0.07
    Negative Logits
    idenote
    -1.54
    iterate
    -1.52
    rÃŃ
    -1.48
    opter
    -1.47
    ophagus
    -1.46
    icio
    -1.44
    olate
    -1.43
    ário
    -1.42
    autre
    -1.41
    atro
    -1.41
    POSITIVE LOGITS
    KY
    1.43
     million
    1.43
     alumni
    1.30
    ew
    1.29
    htaking
    1.29
     resistance
    1.28
     AFL
    1.25
     earlier
    1.24
     ET
    1.24
     hours
    1.23
    Activations Density 4.527%

    No Known Activations