© 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. 28170
    Prev
    Next
    INDEX
    Explanations

    terms related to unsustainability

    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
    375
    +0.14
    0.8%
    369
    +0.13
    0.7%
    214
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.14
    0.02
    180
    +0.13
    0.01
    214
    +0.11
    0.01
    Negative Logits
    backs
    -2.06
    ções
    -1.77
    ees
    -1.75
    ção
    -1.72
    lements
    -1.68
    tion
    -1.63
    ments
    -1.63
    rile
    -1.62
    ttes
    -1.61
     backs
    -1.60
    POSITIVE LOGITS
    Ĥ¬
    1.95
    µ
    1.95
    ¤
    1.86
    ĺ
    1.83
    ibo
    1.80
    ²
    1.76
    Ĵ
    1.75
    ·
    1.72
    ī
    1.72
    ¢
    1.70
    Activations Density 0.066%

    No Known Activations