© 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. 27870
    Prev
    Next
    INDEX
    Explanations

    words indicating economic conditions and discussions around employment

    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
    23
    +0.26
    1.5%
    78
    +0.13
    0.7%
    393
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.26
    0.13
    129
    +0.13
    0.02
    23
    +0.11
    0.13
    Negative Logits
    "}](#
    -2.23
    forge
    -1.86
    itations
    -1.83
    astro
    -1.78
    isters
    -1.77
     programmes
    -1.69
    aceut
    -1.62
    istry
    -1.60
    rooms
    -1.50
    oddsidemargin
    -1.49
    POSITIVE LOGITS
    ł
    2.83
    «
    2.81
    Ĥ
    2.80
    ĩ
    2.79
    ¼
    2.77
    ¦
    2.75
    ↵
    2.75
             ↵
    2.75
    ↵↵↵
    2.75
    <|outofrange|>
    2.75
    Activations Density 2.689%

    No Known Activations