© 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. 1-RES-SM
    11. 27607
    Prev
    Next
    INDEX
    Explanations

    references to atheism or discussions of disbelief in a deity

    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
    290
    +0.13
    0.7%
    321
    +0.13
    0.7%
    300
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.13
    0.02
    386
    +0.13
    0.01
    321
    +0.12
    0.02
    Negative Logits
    į
    -2.59
    Į
    -2.32
    ĺ
    -2.20
    ij
    -2.17
    ĨĴ
    -2.16
    Ł
    -2.10
    Ĭ
    -2.07
    ¶
    -2.06
    ®
    -2.01
    ļ
    -1.99
    POSITIVE LOGITS
    matics
    1.89
    rapeutic
    1.59
    matically
    1.58
    rette
    1.56
    rization
    1.55
    rapy
    1.53
    ster
    1.48
    lium
    1.45
    liche
    1.42
    riz
    1.41
    Activations Density 0.114%

    No Known Activations