© 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 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. 30513
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of entering or accessing something

    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
    267
    +0.12
    0.7%
    343
    +0.12
    0.7%
    358
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.12
    0.01
    317
    +0.12
    0.02
    267
    +0.11
    0.02
    Negative Logits
    unnumbered
    -1.83
    ened
    -1.78
     characterized
    -1.66
    annel
    -1.64
     ABOUT
    -1.54
    iller
    -1.52
    called
    -1.51
    includes
    -1.50
    lessness
    -1.49
    iento
    -1.49
    POSITIVE LOGITS
    prising
    3.04
    prises
    2.42
    prise
    2.19
    tain
    2.09
    tainment
    1.81
    ophone
    1.67
    itol
    1.61
     doors
    1.53
    ococcus
    1.52
     into
    1.50
    Activations Density 0.114%

    No Known Activations