© 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. 27859
    Prev
    Next
    INDEX
    Explanations

    discussions around societal change and the experiences of marginalized groups

    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
    +0.22
    1.3%
    293
    +0.17
    1.0%
    379
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.22
    0.21
    47
    +0.17
    0.20
    190
    +0.14
    0.16
    Negative Logits
    ↵
    -1.95
    ↵            ↵
    -1.95
    <|outofrange|>
    -1.95
    -1.95
    <|outofrange|>
    -1.95
    -1.95
    ↵↵↵
    -1.95
    <|outofrange|>
    -1.95
    <|outofrange|>
    -1.95
    -1.95
    POSITIVE LOGITS
     respectively
    1.65
    film
    1.64
    viron
    1.47
    cient
    1.42
    posed
    1.39
     crops
    1.34
    fty
    1.32
    stadt
    1.30
    inn
    1.29
    itime
    1.29
    Activations Density 8.661%

    No Known Activations