© 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. 4-RES-SM
    11. 11427
    Prev
    Next
    INDEX
    Explanations

    phrases related to email marketing, consent, and user preferences

    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
    78
    +0.16
    0.9%
    89
    +0.13
    0.7%
    469
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.16
    0.09
    154
    +0.13
    0.08
    125
    +0.11
    0.09
    Negative Logits
    ĸ´
    -2.62
    »¿
    -2.36
    ´
    -2.32
    ·¸
    -2.25
    Īĺ
    -2.15
    Į
    -2.05
    ·
    -2.02
    ±
    -2.01
    -2.00
    ↵
    -2.00
    POSITIVE LOGITS
     emails
    2.47
     email
    2.44
     advertisements
    2.41
     payments
    2.28
     downloads
    2.27
     messages
    2.25
     newsletters
    2.24
     purchases
    2.20
     ads
    2.16
     alerts
    2.13
    Activations Density 1.652%

    No Known Activations