© 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. 1-RES-SM
    11. 29114
    Prev
    Next
    INDEX
    Explanations

    instances of phrases related to data collection and acquisition

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    156
    +0.24
    1.4%
    148
    +0.17
    1.0%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.24
    0.02
    308
    +0.17
    0.02
    125
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.66
    ĭ
    -2.38
    §
    -2.28
    ĸ
    -2.25
    ¾
    -2.23
    Ī
    -2.22
    Į
    -2.21
    ®
    -2.13
    Ĩ
    -2.07
    ¿
    -2.05
    POSITIVE LOGITS
    raud
    1.63
    HECK
    1.54
     data
    1.54
     welfare
    1.50
     therefrom
    1.48
    estion
    1.48
     from
    1.48
    ays
    1.40
    ipe
    1.40
     throat
    1.34
    Activations Density 0.090%

    No Known Activations