© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 14063
    Prev
    Next
    INDEX
    Explanations

    phrases related to signing up or registering for services

    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
    302
    +0.12
    0.7%
    21
    +0.10
    0.6%
    170
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    302
    +0.12
    0.08
    329
    +0.10
    0.07
    339
    +0.10
    0.04
    Negative Logits
    ľ
    -4.52
     ↵
    -4.28
    -4.28
    -4.28
    <|outofrange|>
    -4.28
    ↵  ³³³
    -4.28
    -4.28
    č↵
    -4.28
       ↵
    -4.28
    č↵
    -4.28
    POSITIVE LOGITS
     Email
    2.30
     newsletter
    2.28
     email
    2.25
     NOW
    2.08
     anytime
    2.01
     via
    1.96
     your
    1.95
     inbox
    1.95
    email
    1.92
     online
    1.89
    Activations Density 0.845%

    No Known Activations