© 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. 27889
    Prev
    Next
    INDEX
    Explanations

    stylistic elements or attributes in written content

    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
    336
    +0.12
    0.7%
    156
    +0.12
    0.7%
    172
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.12
    0.02
    336
    +0.12
    0.02
    349
    +0.11
    0.02
    Negative Logits
    ĥ½
    -3.01
    ľĵ
    -2.99
    «
    -2.96
    §
    -2.82
    ĵ
    -2.81
    ĥ
    -2.70
    ·
    -2.66
    į
    -2.65
    ¿
    -2.59
    ľ
    -2.59
    POSITIVE LOGITS
    heets
    1.78
    makers
    1.73
    sheet
    1.71
    Sheet
    1.68
    lint
    1.65
     posters
    1.62
    major
    1.61
    wise
    1.60
    nament
    1.55
     appointments
    1.55
    Activations Density 0.093%

    No Known Activations