© 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. 13516
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity or brand associated with cleaning 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
    108
    +0.12
    0.6%
    402
    +0.11
    0.6%
    105
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    349
    +0.12
    0.02
    402
    +0.11
    0.02
    477
    +0.11
    0.02
    Negative Logits
    elf
    -2.13
    apine
    -1.97
    ual
    -1.91
    ular
    -1.81
    icus
    -1.76
    UAL
    -1.60
    ulates
    -1.57
    hang
    -1.55
    itudes
    -1.54
    ridges
    -1.53
    POSITIVE LOGITS
    Ģ
    2.64
    ½
    2.51
    aning
    2.40
    «
    2.35
    ¿½
    2.31
    ī
    2.30
    ħ
    2.28
    ı
    2.24
    ±
    2.22
    ģ
    2.21
    Activations Density 0.156%

    No Known Activations