© 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. 28373
    Prev
    Next
    INDEX
    Explanations

    mentions of the city of Boston and related entities

    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
    +0.18
    1.0%
    410
    +0.16
    0.9%
    71
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.18
    0.03
    410
    +0.16
    0.02
    347
    +0.14
    0.02
    Negative Logits
    Ĥ
    -1.92
    ³
    -1.82
    ayed
    -1.80
    gged
    -1.68
    ²
    -1.65
    ¸
    -1.63
    ¤
    -1.62
    Ł
    -1.61
    ¯
    -1.60
    ters
    -1.58
    POSITIVE LOGITS
    ians
    1.80
    iana
    1.79
    bone
    1.78
    usiness
    1.75
    àµį
    1.71
    antine
    1.71
    opan
    1.71
    ian
    1.67
     Avenue
    1.65
     MHz
    1.62
    Activations Density 0.105%

    No Known Activations