© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 11723
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the state of being or existential affirmations

    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
    156
    +0.15
    0.8%
    430
    +0.14
    0.7%
    418
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.15
    0.01
    31
    +0.14
    0.03
    5
    +0.12
    0.02
    Negative Logits
    t
    -1.84
    s
    -1.65
    gie
    -1.56
     fortune
    -1.53
     dots
    -1.47
    urally
    -1.46
    tz
    -1.42
     picture
    -1.39
     distinction
    -1.39
    matic
    -1.37
    POSITIVE LOGITS
    rael
    2.42
    abeth
    2.41
    heries
    2.35
    covery
    2.17
    tern
    2.10
    quare
    2.00
    chemia
    1.93
    ches
    1.92
    consin
    1.92
    pect
    1.90
    Activations Density 0.147%

    No Known Activations