© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 9297
    Prev
    Next
    INDEX
    Explanations

    different variations and usages of the term "pass" and its related phrases

    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
    493
    +0.13
    0.7%
    263
    +0.12
    0.6%
    219
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    470
    +0.13
    0.03
    493
    +0.12
    0.03
    120
    +0.11
    0.03
    Negative Logits
    le
    -1.68
    woke
    -1.63
     Reporter
    -1.60
    hed
    -1.60
    ised
    -1.57
     basis
    -1.43
    ise
    -1.41
    isation
    -1.40
    lys
    -1.33
     Studios
    -1.33
    POSITIVE LOGITS
    engers
    2.50
    wd
    2.45
    phrase
    2.35
    ports
    2.24
    enger
    2.11
    ionate
    2.06
    entially
    1.99
     through
    1.94
    through
    1.93
    ivity
    1.93
    Activations Density 0.272%

    No Known Activations