© 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. 2-RES-SM
    6. 30285
    Prev
    Next
    INDEX
    Explanations

    instances of the word "however"

    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
    419
    +0.12
    0.7%
    83
    +0.11
    0.6%
    36
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.12
    0.03
    83
    +0.11
    0.02
    120
    +0.11
    0.03
    Negative Logits
     minds
    -1.75
     me
    -1.71
     baths
    -1.66
    ale
    -1.57
     cares
    -1.50
    ropolis
    -1.47
     bath
    -1.44
     thus
    -1.44
     respectively
    -1.42
     smiles
    -1.41
    POSITIVE LOGITS
     progress
    1.71
     unemploy
    1.67
    unreadable
    1.51
    gni
    1.48
    ÑģÑĤвен
    1.45
    fered
    1.39
    tons
    1.37
    ALSE
    1.35
    gradle
    1.34
    semb
    1.34
    Activations Density 0.090%

    No Known Activations